Instructions to use ubergarm/Qwen3.5-397B-A17B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ubergarm/Qwen3.5-397B-A17B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ubergarm/Qwen3.5-397B-A17B-GGUF",
	filename="IQ2_KL/Qwen3.5-397B-A17B-IQ2_KL-00001-of-00004.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ubergarm/Qwen3.5-397B-A17B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Use Docker

docker model run hf.co/ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use ubergarm/Qwen3.5-397B-A17B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubergarm/Qwen3.5-397B-A17B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ubergarm/Qwen3.5-397B-A17B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Ollama
How to use ubergarm/Qwen3.5-397B-A17B-GGUF with Ollama:
```
ollama run hf.co/ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
```

Unsloth Studio

How to use ubergarm/Qwen3.5-397B-A17B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ubergarm/Qwen3.5-397B-A17B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ubergarm/Qwen3.5-397B-A17B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ubergarm/Qwen3.5-397B-A17B-GGUF to start chatting

How to use ubergarm/Qwen3.5-397B-A17B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ubergarm/Qwen3.5-397B-A17B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use ubergarm/Qwen3.5-397B-A17B-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K
```

Lemonade

How to use ubergarm/Qwen3.5-397B-A17B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/Qwen3.5-397B-A17B-GGUF:Q2_K

Run and chat with the model

lemonade run user.Qwen3.5-397B-A17B-GGUF-Q2_K

List all available models

lemonade list

Qwen3.5-397B-A17B-GGUF / logs /quantize-Qwen3.5-397B-A17B-Q3_K.log

ubergarm

provide logs showing imatrix coverage

910390b 4 months ago

Raw

History Blame

164 kB

	# refer to secret recipe in README modelcard

	main: build = 8083 (6fdfce757)
	main: built with GNU 13.3.0 for Linux x86_64
	main: quantizing '/mnt/data/models/ubergarm/Qwen3.5-397B-A17B-GGUF/Qwen3.5-397B-A17B-BF16-00001-of-00017.gguf' to '/mnt/data/models/ubergarm/Qwen3.5-397B-A17B-GGUF/Qwen3.5-397B-A17B-Q3_K.gguf' as Q8_0 using 128 threads
	llama_model_loader: additional 16 GGUFs metadata loaded.
	llama_model_loader: loaded meta data with 46 key-value pairs and 1098 tensors from /mnt/data/models/ubergarm/Qwen3.5-397B-A17B-GGUF/Qwen3.5-397B-A17B-BF16-00001-of-00017.gguf (version GGUF V3 (latest))
	llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
	llama_model_loader: - kv 0: general.architecture str = qwen35moe
	llama_model_loader: - kv 1: general.type str = model
	llama_model_loader: - kv 2: general.sampling.top_k i32 = 20
	llama_model_loader: - kv 3: general.sampling.top_p f32 = 0.950000
	llama_model_loader: - kv 4: general.sampling.temp f32 = 0.600000
	llama_model_loader: - kv 5: general.name str = Qwen3.5 397B A17B
	llama_model_loader: - kv 6: general.basename str = Qwen3.5
	llama_model_loader: - kv 7: general.size_label str = 397B-A17B
	llama_model_loader: - kv 8: general.license str = apache-2.0
	llama_model_loader: - kv 9: general.license.link str = https://huggingface.co/Qwen/Qwen3.5-3...
	llama_model_loader: - kv 10: general.tags arr[str,1] = ["image-text-to-text"]
	llama_model_loader: - kv 11: qwen35moe.block_count u32 = 60
	llama_model_loader: - kv 12: qwen35moe.context_length u32 = 262144
	llama_model_loader: - kv 13: qwen35moe.embedding_length u32 = 4096
	llama_model_loader: - kv 14: qwen35moe.attention.head_count u32 = 32
	llama_model_loader: - kv 15: qwen35moe.attention.head_count_kv u32 = 2
	llama_model_loader: - kv 16: qwen35moe.rope.dimension_sections arr[i32,4] = [11, 11, 10, 0]
	llama_model_loader: - kv 17: qwen35moe.rope.freq_base f32 = 10000000.000000
	llama_model_loader: - kv 18: qwen35moe.attention.layer_norm_rms_epsilon f32 = 0.000001
	llama_model_loader: - kv 19: qwen35moe.expert_count u32 = 512
	llama_model_loader: - kv 20: qwen35moe.expert_used_count u32 = 10
	llama_model_loader: - kv 21: qwen35moe.attention.key_length u32 = 256
	llama_model_loader: - kv 22: qwen35moe.attention.value_length u32 = 256
	llama_model_loader: - kv 23: general.file_type u32 = 32
	llama_model_loader: - kv 24: qwen35moe.expert_feed_forward_length u32 = 1024
	llama_model_loader: - kv 25: qwen35moe.expert_shared_feed_forward_length u32 = 1024
	llama_model_loader: - kv 26: qwen35moe.ssm.conv_kernel u32 = 4
	llama_model_loader: - kv 27: qwen35moe.ssm.state_size u32 = 128
	llama_model_loader: - kv 28: qwen35moe.ssm.group_count u32 = 16
	llama_model_loader: - kv 29: qwen35moe.ssm.time_step_rank u32 = 64
	llama_model_loader: - kv 30: qwen35moe.ssm.inner_size u32 = 8192
	llama_model_loader: - kv 31: qwen35moe.full_attention_interval u32 = 4
	llama_model_loader: - kv 32: qwen35moe.rope.dimension_count u32 = 64
	llama_model_loader: - kv 33: general.quantization_version u32 = 2
	llama_model_loader: - kv 34: tokenizer.ggml.model str = gpt2
	llama_model_loader: - kv 35: tokenizer.ggml.pre str = qwen35
	llama_model_loader: - kv 36: tokenizer.ggml.tokens arr[str,248320] = ["!", "\"", "#", "$", "%", "&", "'", ...
	llama_model_loader: - kv 37: tokenizer.ggml.token_type arr[i32,248320] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
	llama_model_loader: - kv 38: tokenizer.ggml.merges arr[str,247587] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
	llama_model_loader: - kv 39: tokenizer.ggml.eos_token_id u32 = 248046
	llama_model_loader: - kv 40: tokenizer.ggml.padding_token_id u32 = 248044
	llama_model_loader: - kv 41: tokenizer.ggml.add_bos_token bool = false
	llama_model_loader: - kv 42: tokenizer.chat_template str = {%- set image_count = namespace(value...
	llama_model_loader: - kv 43: split.no u16 = 0
	llama_model_loader: - kv 44: split.count u16 = 17
	llama_model_loader: - kv 45: split.tensors.count i32 = 1098
	llama_model_loader: - type f32: 451 tensors
	llama_model_loader: - type bf16: 647 tensors
	================================ Have weights data with 765 entries
	[ 1/1098] output.weight - [ 4096, 248320, 1, 1], type = bf16,
	====== llama_model_quantize_impl: did not find weights for output.weight
	converting to q6_K .. load_imatrix: imatrix datasets=['ubergarm-imatrix-calibration-corpus-v02.txt']
	load_imatrix: loaded 765 importance matrix entries from /mnt/data/models/ubergarm/Qwen3.5-397B-A17B-GGUF/imatrix-Qwen3.5-397B-A17B-BF16-mainline.gguf computed on 829 chunks
	prepare_imatrix: have 765 importance matrix entries
	size = 1940.00 MiB -> 795.70 MiB
	[ 2/1098] output_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 3/1098] token_embd.weight - [ 4096, 248320, 1, 1], type = bf16,
	====== llama_model_quantize_impl: did not find weights for token_embd.weight
	converting to q4_K .. size = 1940.00 MiB -> 545.62 MiB
	[ 4/1098] blk.0.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 5/1098] blk.0.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 6/1098] blk.0.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 7/1098] blk.0.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 8/1098] blk.0.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 9/1098] blk.0.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 10/1098] blk.0.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 11/1098] blk.0.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 12/1098] blk.0.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 13/1098] blk.0.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 14/1098] blk.0.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 15/1098] blk.0.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 16/1098] blk.0.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 17/1098] blk.0.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 18/1098] blk.0.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 19/1098] blk.0.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 20/1098] blk.0.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 21/1098] blk.0.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 22/1098] blk.0.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 23/1098] blk.1.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 24/1098] blk.1.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 25/1098] blk.1.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 26/1098] blk.1.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 27/1098] blk.1.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 28/1098] blk.1.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 29/1098] blk.1.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 30/1098] blk.1.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 31/1098] blk.1.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 32/1098] blk.1.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 33/1098] blk.1.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 34/1098] blk.1.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 35/1098] blk.1.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 36/1098] blk.1.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 37/1098] blk.1.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 38/1098] blk.1.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 39/1098] blk.1.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 40/1098] blk.1.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 41/1098] blk.1.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 42/1098] blk.2.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 43/1098] blk.2.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 44/1098] blk.2.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 45/1098] blk.2.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 46/1098] blk.2.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 47/1098] blk.2.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 48/1098] blk.2.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 49/1098] blk.2.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 50/1098] blk.2.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 51/1098] blk.2.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 52/1098] blk.2.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 53/1098] blk.2.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 54/1098] blk.2.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 55/1098] blk.2.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 56/1098] blk.2.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 57/1098] blk.2.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 58/1098] blk.2.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 59/1098] blk.2.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 60/1098] blk.2.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 61/1098] blk.3.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 62/1098] blk.3.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 63/1098] blk.3.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 64/1098] blk.3.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 65/1098] blk.3.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 66/1098] blk.3.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 67/1098] blk.3.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 68/1098] blk.3.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 69/1098] blk.3.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 70/1098] blk.3.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 71/1098] blk.3.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 72/1098] blk.3.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 73/1098] blk.3.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 74/1098] blk.3.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 75/1098] blk.3.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 76/1098] blk.3.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 77/1098] blk.4.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 78/1098] blk.4.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 79/1098] blk.4.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 80/1098] blk.4.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 81/1098] blk.4.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 82/1098] blk.4.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 83/1098] blk.4.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 84/1098] blk.4.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 85/1098] blk.4.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 86/1098] blk.4.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 87/1098] blk.4.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 88/1098] blk.4.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 89/1098] blk.4.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 90/1098] blk.4.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 91/1098] blk.4.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 92/1098] blk.4.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 93/1098] blk.4.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 94/1098] blk.4.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 95/1098] blk.4.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 96/1098] blk.5.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 97/1098] blk.5.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 98/1098] blk.5.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 99/1098] blk.5.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 100/1098] blk.5.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 101/1098] blk.5.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 102/1098] blk.5.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 103/1098] blk.5.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 104/1098] blk.5.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 105/1098] blk.5.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 106/1098] blk.5.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 107/1098] blk.5.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 108/1098] blk.5.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 109/1098] blk.5.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 110/1098] blk.5.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 111/1098] blk.5.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 112/1098] blk.5.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 113/1098] blk.5.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 114/1098] blk.5.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 115/1098] blk.6.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 116/1098] blk.6.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 117/1098] blk.6.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 118/1098] blk.6.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 119/1098] blk.6.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 120/1098] blk.6.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 121/1098] blk.6.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 122/1098] blk.6.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 123/1098] blk.6.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 124/1098] blk.6.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 125/1098] blk.6.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 126/1098] blk.6.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 127/1098] blk.6.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 128/1098] blk.6.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 129/1098] blk.6.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 130/1098] blk.6.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 131/1098] blk.6.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 132/1098] blk.6.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 133/1098] blk.6.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 134/1098] blk.7.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 135/1098] blk.7.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 136/1098] blk.7.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 137/1098] blk.7.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 138/1098] blk.7.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 139/1098] blk.7.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 140/1098] blk.7.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 141/1098] blk.7.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 142/1098] blk.7.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 143/1098] blk.7.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 144/1098] blk.7.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 145/1098] blk.7.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 146/1098] blk.7.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 147/1098] blk.7.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 148/1098] blk.7.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 149/1098] blk.7.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 150/1098] blk.8.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 151/1098] blk.8.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 152/1098] blk.8.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 153/1098] blk.8.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 154/1098] blk.8.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 155/1098] blk.8.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 156/1098] blk.8.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 157/1098] blk.8.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 158/1098] blk.8.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 159/1098] blk.8.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 160/1098] blk.8.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 161/1098] blk.8.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 162/1098] blk.8.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 163/1098] blk.8.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 164/1098] blk.8.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 165/1098] blk.8.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 166/1098] blk.8.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 167/1098] blk.8.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 168/1098] blk.8.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 169/1098] blk.9.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 170/1098] blk.9.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 171/1098] blk.9.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 172/1098] blk.9.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 173/1098] blk.9.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 174/1098] blk.9.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 175/1098] blk.9.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 176/1098] blk.9.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 177/1098] blk.9.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 178/1098] blk.9.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 179/1098] blk.9.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 180/1098] blk.9.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 181/1098] blk.9.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 182/1098] blk.9.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 183/1098] blk.9.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 184/1098] blk.9.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 185/1098] blk.9.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 186/1098] blk.9.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 187/1098] blk.9.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 188/1098] blk.10.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 189/1098] blk.10.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 190/1098] blk.10.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 191/1098] blk.10.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 192/1098] blk.10.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 193/1098] blk.10.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 194/1098] blk.10.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 195/1098] blk.10.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 196/1098] blk.10.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 197/1098] blk.10.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 198/1098] blk.10.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 199/1098] blk.10.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 200/1098] blk.10.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 201/1098] blk.10.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 202/1098] blk.10.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 203/1098] blk.10.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 204/1098] blk.10.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 205/1098] blk.10.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 206/1098] blk.10.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 207/1098] blk.11.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 208/1098] blk.11.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 209/1098] blk.11.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 210/1098] blk.11.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 211/1098] blk.11.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 212/1098] blk.11.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 213/1098] blk.11.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 214/1098] blk.11.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 215/1098] blk.11.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 216/1098] blk.11.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 217/1098] blk.11.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 218/1098] blk.11.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 219/1098] blk.11.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 220/1098] blk.11.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 221/1098] blk.11.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 222/1098] blk.11.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 223/1098] blk.12.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 224/1098] blk.12.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 225/1098] blk.12.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 226/1098] blk.12.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 227/1098] blk.12.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 228/1098] blk.12.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 229/1098] blk.12.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 230/1098] blk.12.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 231/1098] blk.12.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 232/1098] blk.12.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 233/1098] blk.12.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 234/1098] blk.12.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 235/1098] blk.12.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 236/1098] blk.12.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 237/1098] blk.12.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 238/1098] blk.12.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 239/1098] blk.12.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 240/1098] blk.12.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 241/1098] blk.12.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 242/1098] blk.13.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 243/1098] blk.13.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 244/1098] blk.13.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 245/1098] blk.13.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 246/1098] blk.13.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 247/1098] blk.13.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 248/1098] blk.13.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 249/1098] blk.13.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 250/1098] blk.13.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 251/1098] blk.13.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 252/1098] blk.13.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 253/1098] blk.13.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 254/1098] blk.13.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 255/1098] blk.13.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 256/1098] blk.13.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 257/1098] blk.13.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 258/1098] blk.13.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 259/1098] blk.13.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 260/1098] blk.13.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 261/1098] blk.14.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 262/1098] blk.14.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 263/1098] blk.14.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 264/1098] blk.14.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 265/1098] blk.14.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 266/1098] blk.14.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 267/1098] blk.14.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 268/1098] blk.14.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 269/1098] blk.14.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 270/1098] blk.14.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 271/1098] blk.14.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 272/1098] blk.14.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 273/1098] blk.14.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 274/1098] blk.14.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 275/1098] blk.14.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 276/1098] blk.14.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 277/1098] blk.14.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 278/1098] blk.14.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 279/1098] blk.14.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 280/1098] blk.15.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 281/1098] blk.15.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 282/1098] blk.15.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 283/1098] blk.15.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 284/1098] blk.15.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 285/1098] blk.15.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 286/1098] blk.15.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 287/1098] blk.15.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 288/1098] blk.15.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 289/1098] blk.15.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 290/1098] blk.15.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 291/1098] blk.15.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 292/1098] blk.15.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 293/1098] blk.15.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 294/1098] blk.15.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 295/1098] blk.15.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 296/1098] blk.16.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 297/1098] blk.16.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 298/1098] blk.16.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 299/1098] blk.16.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 300/1098] blk.16.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 301/1098] blk.16.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 302/1098] blk.16.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 303/1098] blk.16.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 304/1098] blk.16.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 305/1098] blk.16.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 306/1098] blk.16.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 307/1098] blk.16.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 308/1098] blk.16.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 309/1098] blk.16.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 310/1098] blk.16.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 311/1098] blk.16.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 312/1098] blk.16.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 313/1098] blk.16.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 314/1098] blk.16.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 315/1098] blk.17.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 316/1098] blk.17.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 317/1098] blk.17.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 318/1098] blk.17.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 319/1098] blk.17.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 320/1098] blk.17.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 321/1098] blk.17.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 322/1098] blk.17.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 323/1098] blk.17.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 324/1098] blk.17.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 325/1098] blk.17.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 326/1098] blk.17.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 327/1098] blk.17.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 328/1098] blk.17.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 329/1098] blk.17.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 330/1098] blk.17.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 331/1098] blk.17.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 332/1098] blk.17.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 333/1098] blk.17.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 334/1098] blk.18.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 335/1098] blk.18.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 336/1098] blk.18.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 337/1098] blk.18.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 338/1098] blk.18.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 339/1098] blk.18.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 340/1098] blk.18.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 341/1098] blk.18.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 342/1098] blk.18.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 343/1098] blk.18.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 344/1098] blk.18.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 345/1098] blk.18.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 346/1098] blk.18.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 347/1098] blk.18.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 348/1098] blk.18.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 349/1098] blk.18.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 350/1098] blk.18.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 351/1098] blk.18.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 352/1098] blk.18.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 353/1098] blk.19.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 354/1098] blk.19.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 355/1098] blk.19.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 356/1098] blk.19.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 357/1098] blk.19.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 358/1098] blk.19.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 359/1098] blk.19.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 360/1098] blk.19.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 361/1098] blk.19.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 362/1098] blk.19.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 363/1098] blk.19.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 364/1098] blk.19.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 365/1098] blk.19.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 366/1098] blk.19.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 367/1098] blk.19.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 368/1098] blk.19.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 369/1098] blk.20.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 370/1098] blk.20.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 371/1098] blk.20.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 372/1098] blk.20.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 373/1098] blk.20.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 374/1098] blk.20.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 375/1098] blk.20.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 376/1098] blk.20.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 377/1098] blk.20.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 378/1098] blk.20.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 379/1098] blk.20.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 380/1098] blk.20.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 381/1098] blk.20.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 382/1098] blk.20.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 383/1098] blk.20.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 384/1098] blk.20.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 385/1098] blk.20.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 386/1098] blk.20.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 387/1098] blk.20.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 388/1098] blk.21.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 389/1098] blk.21.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 390/1098] blk.21.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 391/1098] blk.21.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 392/1098] blk.21.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 393/1098] blk.21.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 394/1098] blk.21.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 395/1098] blk.21.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 396/1098] blk.21.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 397/1098] blk.21.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 398/1098] blk.21.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 399/1098] blk.21.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 400/1098] blk.21.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 401/1098] blk.21.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 402/1098] blk.21.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 403/1098] blk.21.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 404/1098] blk.21.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 405/1098] blk.21.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 406/1098] blk.21.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 407/1098] blk.22.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 408/1098] blk.22.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 409/1098] blk.22.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 410/1098] blk.22.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 411/1098] blk.22.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 412/1098] blk.22.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 413/1098] blk.22.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 414/1098] blk.22.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 415/1098] blk.22.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 416/1098] blk.22.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 417/1098] blk.22.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 418/1098] blk.22.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 419/1098] blk.22.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 420/1098] blk.22.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 421/1098] blk.22.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 422/1098] blk.22.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 423/1098] blk.22.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 424/1098] blk.22.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 425/1098] blk.22.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 426/1098] blk.23.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 427/1098] blk.23.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 428/1098] blk.23.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 429/1098] blk.23.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 430/1098] blk.23.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 431/1098] blk.23.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 432/1098] blk.23.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 433/1098] blk.23.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 434/1098] blk.23.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 435/1098] blk.23.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 436/1098] blk.23.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 437/1098] blk.23.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 438/1098] blk.23.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 439/1098] blk.23.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 440/1098] blk.23.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 441/1098] blk.23.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 442/1098] blk.24.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 443/1098] blk.24.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 444/1098] blk.24.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 445/1098] blk.24.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 446/1098] blk.24.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 447/1098] blk.24.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 448/1098] blk.24.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 449/1098] blk.24.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 450/1098] blk.24.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 451/1098] blk.24.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 452/1098] blk.24.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 453/1098] blk.24.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 454/1098] blk.24.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 455/1098] blk.24.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 456/1098] blk.24.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 457/1098] blk.24.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 458/1098] blk.24.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 459/1098] blk.24.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 460/1098] blk.24.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 461/1098] blk.25.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 462/1098] blk.25.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 463/1098] blk.25.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 464/1098] blk.25.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 465/1098] blk.25.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 466/1098] blk.25.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 467/1098] blk.25.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 468/1098] blk.25.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 469/1098] blk.25.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 470/1098] blk.25.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 471/1098] blk.25.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 472/1098] blk.25.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 473/1098] blk.25.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 474/1098] blk.25.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 475/1098] blk.25.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 476/1098] blk.25.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 477/1098] blk.25.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 478/1098] blk.25.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 479/1098] blk.25.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 480/1098] blk.26.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 481/1098] blk.26.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 482/1098] blk.26.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 483/1098] blk.26.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 484/1098] blk.26.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 485/1098] blk.26.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 486/1098] blk.26.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 487/1098] blk.26.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 488/1098] blk.26.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 489/1098] blk.26.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 490/1098] blk.26.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 491/1098] blk.26.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 492/1098] blk.26.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 493/1098] blk.26.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 494/1098] blk.26.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 495/1098] blk.26.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 496/1098] blk.26.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 497/1098] blk.26.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 498/1098] blk.26.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 499/1098] blk.27.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 500/1098] blk.27.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 501/1098] blk.27.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 502/1098] blk.27.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 503/1098] blk.27.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 504/1098] blk.27.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 505/1098] blk.27.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 506/1098] blk.27.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 507/1098] blk.27.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 508/1098] blk.27.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 509/1098] blk.27.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 510/1098] blk.27.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 511/1098] blk.27.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 512/1098] blk.27.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 513/1098] blk.27.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 514/1098] blk.27.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 515/1098] blk.28.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 516/1098] blk.28.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 517/1098] blk.28.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 518/1098] blk.28.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 519/1098] blk.28.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 520/1098] blk.28.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 521/1098] blk.28.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 522/1098] blk.28.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 523/1098] blk.28.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 524/1098] blk.28.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 525/1098] blk.28.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 526/1098] blk.28.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 527/1098] blk.28.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 528/1098] blk.28.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 529/1098] blk.28.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 530/1098] blk.28.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 531/1098] blk.28.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 532/1098] blk.28.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 533/1098] blk.28.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 534/1098] blk.29.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 535/1098] blk.29.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 536/1098] blk.29.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 537/1098] blk.29.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 538/1098] blk.29.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 539/1098] blk.29.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 540/1098] blk.29.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 541/1098] blk.29.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 542/1098] blk.29.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 543/1098] blk.29.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 544/1098] blk.29.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 545/1098] blk.29.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 546/1098] blk.29.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 547/1098] blk.29.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 548/1098] blk.29.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 549/1098] blk.29.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 550/1098] blk.29.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 551/1098] blk.29.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 552/1098] blk.29.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 553/1098] blk.30.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 554/1098] blk.30.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 555/1098] blk.30.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 556/1098] blk.30.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 557/1098] blk.30.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 558/1098] blk.30.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 559/1098] blk.30.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 560/1098] blk.30.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 561/1098] blk.30.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 562/1098] blk.30.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 563/1098] blk.30.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 564/1098] blk.30.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 565/1098] blk.30.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 566/1098] blk.30.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 567/1098] blk.30.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 568/1098] blk.30.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 569/1098] blk.30.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 570/1098] blk.30.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 571/1098] blk.30.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 572/1098] blk.31.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 573/1098] blk.31.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 574/1098] blk.31.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 575/1098] blk.31.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 576/1098] blk.31.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 577/1098] blk.31.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 578/1098] blk.31.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 579/1098] blk.31.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 580/1098] blk.31.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 581/1098] blk.31.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 582/1098] blk.31.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 583/1098] blk.31.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 584/1098] blk.31.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 585/1098] blk.31.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 586/1098] blk.31.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 587/1098] blk.31.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 588/1098] blk.32.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 589/1098] blk.32.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 590/1098] blk.32.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 591/1098] blk.32.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 592/1098] blk.32.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 593/1098] blk.32.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 594/1098] blk.32.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 595/1098] blk.32.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 596/1098] blk.32.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 597/1098] blk.32.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 598/1098] blk.32.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 599/1098] blk.32.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 600/1098] blk.32.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 601/1098] blk.32.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 602/1098] blk.32.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 603/1098] blk.32.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 604/1098] blk.32.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 605/1098] blk.32.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 606/1098] blk.32.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 607/1098] blk.33.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 608/1098] blk.33.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 609/1098] blk.33.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 610/1098] blk.33.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 611/1098] blk.33.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 612/1098] blk.33.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 613/1098] blk.33.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 614/1098] blk.33.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 615/1098] blk.33.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 616/1098] blk.33.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 617/1098] blk.33.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 618/1098] blk.33.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 619/1098] blk.33.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 620/1098] blk.33.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 621/1098] blk.33.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 622/1098] blk.33.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 623/1098] blk.33.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 624/1098] blk.33.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 625/1098] blk.33.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 626/1098] blk.34.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 627/1098] blk.34.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 628/1098] blk.34.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 629/1098] blk.34.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 630/1098] blk.34.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 631/1098] blk.34.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 632/1098] blk.34.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 633/1098] blk.34.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 634/1098] blk.34.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 635/1098] blk.34.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 636/1098] blk.34.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 637/1098] blk.34.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 638/1098] blk.34.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 639/1098] blk.34.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 640/1098] blk.34.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 641/1098] blk.34.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 642/1098] blk.34.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 643/1098] blk.34.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 644/1098] blk.34.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 645/1098] blk.35.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 646/1098] blk.35.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 647/1098] blk.35.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 648/1098] blk.35.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 649/1098] blk.35.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 650/1098] blk.35.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 651/1098] blk.35.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 652/1098] blk.35.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 653/1098] blk.35.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 654/1098] blk.35.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 655/1098] blk.35.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 656/1098] blk.35.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 657/1098] blk.35.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 658/1098] blk.35.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 659/1098] blk.35.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 660/1098] blk.35.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 661/1098] blk.36.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 662/1098] blk.36.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 663/1098] blk.36.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 664/1098] blk.36.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 665/1098] blk.36.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 666/1098] blk.36.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 667/1098] blk.36.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 668/1098] blk.36.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 669/1098] blk.36.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 670/1098] blk.36.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 671/1098] blk.36.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 672/1098] blk.36.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 673/1098] blk.36.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 674/1098] blk.36.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 675/1098] blk.36.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 676/1098] blk.36.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 677/1098] blk.36.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 678/1098] blk.36.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 679/1098] blk.36.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 680/1098] blk.37.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 681/1098] blk.37.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 682/1098] blk.37.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 683/1098] blk.37.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 684/1098] blk.37.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 685/1098] blk.37.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 686/1098] blk.37.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 687/1098] blk.37.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 688/1098] blk.37.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 689/1098] blk.37.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 690/1098] blk.37.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 691/1098] blk.37.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 692/1098] blk.37.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 693/1098] blk.37.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 694/1098] blk.37.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 695/1098] blk.37.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 696/1098] blk.37.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 697/1098] blk.37.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 698/1098] blk.37.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 699/1098] blk.38.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 700/1098] blk.38.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 701/1098] blk.38.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 702/1098] blk.38.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 703/1098] blk.38.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 704/1098] blk.38.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 705/1098] blk.38.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 706/1098] blk.38.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 707/1098] blk.38.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 708/1098] blk.38.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 709/1098] blk.38.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 710/1098] blk.38.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 711/1098] blk.38.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 712/1098] blk.38.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 713/1098] blk.38.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 714/1098] blk.38.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 715/1098] blk.38.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 716/1098] blk.38.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 717/1098] blk.38.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 718/1098] blk.39.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 719/1098] blk.39.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 720/1098] blk.39.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 721/1098] blk.39.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 722/1098] blk.39.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 723/1098] blk.39.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 724/1098] blk.39.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 725/1098] blk.39.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 726/1098] blk.39.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 727/1098] blk.39.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 728/1098] blk.39.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 729/1098] blk.39.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 730/1098] blk.39.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 731/1098] blk.39.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 732/1098] blk.39.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 733/1098] blk.39.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 734/1098] blk.40.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 735/1098] blk.40.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 736/1098] blk.40.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 737/1098] blk.40.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 738/1098] blk.40.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 739/1098] blk.40.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 740/1098] blk.40.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 741/1098] blk.40.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 742/1098] blk.40.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 743/1098] blk.40.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 744/1098] blk.40.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 745/1098] blk.40.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 746/1098] blk.40.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 747/1098] blk.40.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 748/1098] blk.40.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 749/1098] blk.40.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 750/1098] blk.40.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 751/1098] blk.40.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 752/1098] blk.40.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 753/1098] blk.41.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 754/1098] blk.41.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 755/1098] blk.41.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 756/1098] blk.41.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 757/1098] blk.41.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 758/1098] blk.41.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 759/1098] blk.41.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 760/1098] blk.41.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 761/1098] blk.41.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 762/1098] blk.41.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 763/1098] blk.41.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 764/1098] blk.41.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 765/1098] blk.41.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 766/1098] blk.41.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 767/1098] blk.41.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 768/1098] blk.41.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 769/1098] blk.41.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 770/1098] blk.41.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 771/1098] blk.41.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 772/1098] blk.42.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 773/1098] blk.42.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 774/1098] blk.42.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 775/1098] blk.42.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 776/1098] blk.42.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 777/1098] blk.42.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 778/1098] blk.42.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 779/1098] blk.42.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 780/1098] blk.42.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 781/1098] blk.42.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 782/1098] blk.42.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 783/1098] blk.42.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 784/1098] blk.42.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 785/1098] blk.42.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 786/1098] blk.42.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 787/1098] blk.42.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 788/1098] blk.42.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 789/1098] blk.42.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 790/1098] blk.42.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 791/1098] blk.43.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 792/1098] blk.43.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 793/1098] blk.43.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 794/1098] blk.43.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 795/1098] blk.43.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 796/1098] blk.43.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 797/1098] blk.43.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 798/1098] blk.43.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 799/1098] blk.43.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 800/1098] blk.43.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 801/1098] blk.43.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 802/1098] blk.43.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 803/1098] blk.43.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 804/1098] blk.43.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 805/1098] blk.43.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 806/1098] blk.43.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 807/1098] blk.44.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 808/1098] blk.44.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 809/1098] blk.44.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 810/1098] blk.44.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 811/1098] blk.44.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 812/1098] blk.44.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 813/1098] blk.44.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 814/1098] blk.44.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 815/1098] blk.44.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 816/1098] blk.44.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 817/1098] blk.44.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 818/1098] blk.44.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 819/1098] blk.44.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 820/1098] blk.44.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 821/1098] blk.44.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 822/1098] blk.44.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 823/1098] blk.44.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 824/1098] blk.44.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 825/1098] blk.44.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 826/1098] blk.45.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 827/1098] blk.45.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 828/1098] blk.45.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 829/1098] blk.45.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 830/1098] blk.45.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 831/1098] blk.45.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 832/1098] blk.45.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 833/1098] blk.45.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 834/1098] blk.45.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 835/1098] blk.45.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 836/1098] blk.45.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 837/1098] blk.45.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 838/1098] blk.45.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 839/1098] blk.45.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 840/1098] blk.45.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 841/1098] blk.45.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 842/1098] blk.45.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 843/1098] blk.45.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 844/1098] blk.45.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 845/1098] blk.46.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 846/1098] blk.46.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 847/1098] blk.46.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 848/1098] blk.46.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 849/1098] blk.46.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 850/1098] blk.46.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 851/1098] blk.46.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 852/1098] blk.46.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 853/1098] blk.46.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 854/1098] blk.46.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 855/1098] blk.46.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 856/1098] blk.46.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 857/1098] blk.46.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 858/1098] blk.46.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 859/1098] blk.46.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 860/1098] blk.46.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 861/1098] blk.46.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 862/1098] blk.46.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 863/1098] blk.46.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 864/1098] blk.47.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 865/1098] blk.47.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 866/1098] blk.47.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 867/1098] blk.47.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 868/1098] blk.47.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 869/1098] blk.47.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 870/1098] blk.47.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 871/1098] blk.47.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 872/1098] blk.47.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 873/1098] blk.47.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 874/1098] blk.47.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 875/1098] blk.47.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 876/1098] blk.47.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 877/1098] blk.47.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 878/1098] blk.47.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 879/1098] blk.47.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 880/1098] blk.48.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 881/1098] blk.48.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 882/1098] blk.48.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 883/1098] blk.48.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 884/1098] blk.48.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 885/1098] blk.48.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 886/1098] blk.48.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 887/1098] blk.48.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 888/1098] blk.48.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 889/1098] blk.48.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 890/1098] blk.48.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 891/1098] blk.48.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 892/1098] blk.48.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 893/1098] blk.48.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 894/1098] blk.48.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 895/1098] blk.48.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 896/1098] blk.48.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 897/1098] blk.48.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 898/1098] blk.48.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 899/1098] blk.49.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 900/1098] blk.49.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 901/1098] blk.49.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 902/1098] blk.49.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 903/1098] blk.49.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 904/1098] blk.49.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 905/1098] blk.49.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 906/1098] blk.49.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 907/1098] blk.49.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 908/1098] blk.49.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 909/1098] blk.49.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 910/1098] blk.49.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 911/1098] blk.49.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 912/1098] blk.49.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 913/1098] blk.49.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 914/1098] blk.49.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 915/1098] blk.49.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 916/1098] blk.49.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 917/1098] blk.49.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 918/1098] blk.50.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 919/1098] blk.50.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 920/1098] blk.50.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 921/1098] blk.50.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 922/1098] blk.50.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 923/1098] blk.50.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 924/1098] blk.50.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 925/1098] blk.50.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 926/1098] blk.50.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 927/1098] blk.50.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 928/1098] blk.50.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 929/1098] blk.50.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 930/1098] blk.50.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 931/1098] blk.50.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 932/1098] blk.50.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 933/1098] blk.50.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 934/1098] blk.50.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 935/1098] blk.50.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 936/1098] blk.50.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 937/1098] blk.51.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 938/1098] blk.51.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 939/1098] blk.51.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 940/1098] blk.51.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 941/1098] blk.51.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[ 942/1098] blk.51.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[ 943/1098] blk.51.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[ 944/1098] blk.51.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 945/1098] blk.51.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 946/1098] blk.51.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 947/1098] blk.51.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 948/1098] blk.51.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 949/1098] blk.51.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 950/1098] blk.51.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 951/1098] blk.51.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 952/1098] blk.51.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 953/1098] blk.52.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 954/1098] blk.52.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 955/1098] blk.52.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 956/1098] blk.52.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 957/1098] blk.52.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 958/1098] blk.52.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 959/1098] blk.52.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 960/1098] blk.52.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 961/1098] blk.52.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 962/1098] blk.52.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 963/1098] blk.52.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 964/1098] blk.52.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 965/1098] blk.52.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 966/1098] blk.52.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 967/1098] blk.52.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 968/1098] blk.52.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 969/1098] blk.52.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 970/1098] blk.52.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 971/1098] blk.52.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 972/1098] blk.53.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 973/1098] blk.53.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 974/1098] blk.53.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 975/1098] blk.53.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 976/1098] blk.53.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 977/1098] blk.53.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 978/1098] blk.53.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 979/1098] blk.53.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 980/1098] blk.53.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 981/1098] blk.53.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 982/1098] blk.53.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 983/1098] blk.53.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 984/1098] blk.53.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 985/1098] blk.53.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 986/1098] blk.53.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[ 987/1098] blk.53.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[ 988/1098] blk.53.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 989/1098] blk.53.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[ 990/1098] blk.53.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 991/1098] blk.54.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[ 992/1098] blk.54.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 993/1098] blk.54.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[ 994/1098] blk.54.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[ 995/1098] blk.54.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[ 996/1098] blk.54.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[ 997/1098] blk.54.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[ 998/1098] blk.54.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[ 999/1098] blk.54.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1000/1098] blk.54.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1001/1098] blk.54.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1002/1098] blk.54.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1003/1098] blk.54.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[1004/1098] blk.54.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[1005/1098] blk.54.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[1006/1098] blk.54.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[1007/1098] blk.54.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[1008/1098] blk.54.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[1009/1098] blk.54.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[1010/1098] blk.55.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[1011/1098] blk.55.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[1012/1098] blk.55.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1013/1098] blk.55.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[1014/1098] blk.55.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[1015/1098] blk.55.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[1016/1098] blk.55.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[1017/1098] blk.55.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[1018/1098] blk.55.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1019/1098] blk.55.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1020/1098] blk.55.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[1021/1098] blk.55.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1022/1098] blk.55.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1023/1098] blk.55.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1024/1098] blk.55.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1025/1098] blk.55.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1026/1098] blk.56.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[1027/1098] blk.56.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1028/1098] blk.56.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[1029/1098] blk.56.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[1030/1098] blk.56.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1031/1098] blk.56.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1032/1098] blk.56.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[1033/1098] blk.56.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1034/1098] blk.56.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1035/1098] blk.56.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1036/1098] blk.56.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1037/1098] blk.56.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1038/1098] blk.56.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[1039/1098] blk.56.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[1040/1098] blk.56.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[1041/1098] blk.56.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[1042/1098] blk.56.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[1043/1098] blk.56.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[1044/1098] blk.56.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[1045/1098] blk.57.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[1046/1098] blk.57.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1047/1098] blk.57.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[1048/1098] blk.57.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[1049/1098] blk.57.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1050/1098] blk.57.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1051/1098] blk.57.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[1052/1098] blk.57.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1053/1098] blk.57.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1054/1098] blk.57.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1055/1098] blk.57.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1056/1098] blk.57.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1057/1098] blk.57.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[1058/1098] blk.57.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[1059/1098] blk.57.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[1060/1098] blk.57.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[1061/1098] blk.57.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[1062/1098] blk.57.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[1063/1098] blk.57.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[1064/1098] blk.58.attn_gate.weight - [ 4096, 8192, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[1065/1098] blk.58.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1066/1098] blk.58.attn_qkv.weight - [ 4096, 12288, 1, 1], type = bf16, converting to q8_0 .. size = 96.00 MiB -> 51.00 MiB
	[1067/1098] blk.58.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[1068/1098] blk.58.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1069/1098] blk.58.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1070/1098] blk.58.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[1071/1098] blk.58.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1072/1098] blk.58.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1073/1098] blk.58.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1074/1098] blk.58.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1075/1098] blk.58.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1076/1098] blk.58.ssm_a - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[1077/1098] blk.58.ssm_alpha.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[1078/1098] blk.58.ssm_beta.weight - [ 4096, 64, 1, 1], type = bf16, converting to q8_0 .. size = 0.50 MiB -> 0.27 MiB
	[1079/1098] blk.58.ssm_conv1d.weight - [ 4, 12288, 1, 1], type = f32, size = 0.188 MiB
	[1080/1098] blk.58.ssm_dt.bias - [ 64, 1, 1, 1], type = f32, size = 0.000 MiB
	[1081/1098] blk.58.ssm_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB
	[1082/1098] blk.58.ssm_out.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[1083/1098] blk.59.attn_k.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[1084/1098] blk.59.attn_k_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[1085/1098] blk.59.attn_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1086/1098] blk.59.attn_output.weight - [ 8192, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 64.00 MiB -> 34.00 MiB
	[1087/1098] blk.59.attn_q.weight - [ 4096, 16384, 1, 1], type = bf16, converting to q8_0 .. size = 128.00 MiB -> 68.00 MiB
	[1088/1098] blk.59.attn_q_norm.weight - [ 256, 1, 1, 1], type = f32, size = 0.001 MiB
	[1089/1098] blk.59.attn_v.weight - [ 4096, 512, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB
	[1090/1098] blk.59.ffn_down_exps.weight - [ 1024, 4096, 512, 1], type = bf16, (manual override: q8_0 -> q4_K) converting to q4_K .. size = 4096.00 MiB -> 1152.00 MiB
	[1091/1098] blk.59.ffn_down_shexp.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1092/1098] blk.59.ffn_gate_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1093/1098] blk.59.ffn_gate_inp.weight - [ 4096, 512, 1, 1], type = f32, size = 8.000 MiB
	[1094/1098] blk.59.ffn_gate_inp_shexp.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	[1095/1098] blk.59.ffn_gate_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1096/1098] blk.59.ffn_up_exps.weight - [ 4096, 1024, 512, 1], type = bf16, (manual override: q8_0 -> q3_K) converting to q3_K .. size = 4096.00 MiB -> 880.00 MiB
	[1097/1098] blk.59.ffn_up_shexp.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB
	[1098/1098] blk.59.post_attention_norm.weight - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB
	llama_model_quantize_impl: model size = 756216.34 MiB
	llama_model_quantize_impl: quant size = 184290.32 MiB

	main: quantize time = 693851.09 ms
	main: total time = 693851.09 ms