Instructions to use ubergarm/Qwen3.5-122B-A10B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ubergarm/Qwen3.5-122B-A10B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ubergarm/Qwen3.5-122B-A10B-GGUF",
	filename="Qwen3.5-122B-A10B-IQ1_KT.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/Qwen3.5-122B-A10B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf ubergarm/Qwen3.5-122B-A10B-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/Qwen3.5-122B-A10B-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/Qwen3.5-122B-A10B-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/Qwen3.5-122B-A10B-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

Use Docker

docker model run hf.co/ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use ubergarm/Qwen3.5-122B-A10B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubergarm/Qwen3.5-122B-A10B-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/Qwen3.5-122B-A10B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

Ollama
How to use ubergarm/Qwen3.5-122B-A10B-GGUF with Ollama:
```
ollama run hf.co/ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K
```

Unsloth Studio

How to use ubergarm/Qwen3.5-122B-A10B-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/Qwen3.5-122B-A10B-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/Qwen3.5-122B-A10B-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/Qwen3.5-122B-A10B-GGUF to start chatting

How to use ubergarm/Qwen3.5-122B-A10B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ubergarm/Qwen3.5-122B-A10B-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/Qwen3.5-122B-A10B-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ubergarm/Qwen3.5-122B-A10B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ubergarm/Qwen3.5-122B-A10B-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/Qwen3.5-122B-A10B-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use ubergarm/Qwen3.5-122B-A10B-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K
```

Lemonade

How to use ubergarm/Qwen3.5-122B-A10B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/Qwen3.5-122B-A10B-GGUF:Q2_K

Run and chat with the model

lemonade run user.Qwen3.5-122B-A10B-GGUF-Q2_K

List all available models

lemonade list

Testing smol-IQ5_KS

#13

by shewin - opened Apr 10

Discussion

shewin

Apr 10

Tensor blk.47.ffn_down_exps.weight (size = 507.00 MiB) buffer type overriden to CUDA_Host

Allocating 71.86 GiB of pinned host memory, this may take a while.
Using pinned host memory improves PP performance by a significant margin.
But if it takes too long for your model and amount of patience, kill the process and run using

GGML_CUDA_NO_PINNED=1 your_command_goes_here
done allocating 71.86 GiB in 19893.7 ms

llm_load_tensors: offloading 48 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 49/49 layers to GPU
llm_load_tensors: CUDA_Host buffer size = 73588.97 MiB
llm_load_tensors: CUDA0 buffer size = 5607.73 MiB
...................................................................................................~ggml_backend_cuda_context: have 0 graphs
.
llama_init_from_model: n_ctx = 250112
llama_init_from_model: n_batch = 8096
llama_init_from_model: n_ubatch = 8096
llama_init_from_model: flash_attn = 1
llama_init_from_model: attn_max_b = 8096
llama_init_from_model: fused_moe = 1
llama_init_from_model: grouped er = 1
llama_init_from_model: fused_up_gate = 1
llama_init_from_model: fused_mmad = 1
llama_init_from_model: rope_cache = 0
llama_init_from_model: graph_reuse = 1
llama_init_from_model: k_cache_hadam = 0
llama_init_from_model: v_cache_hadam = 0
llama_init_from_model: split_mode_graph_scheduling = 0
llama_init_from_model: reduce_type = f16
llama_init_from_model: sched_async = 0
llama_init_from_model: ser = -1, 0
llama_init_from_model: freq_base = 10000000.0
llama_init_from_model: freq_scale = 1
llama_kv_cache_init: CUDA0 KV buffer size = 6011.06 MiB
llama_init_from_model: KV self size = 5862.00 MiB, K (f16): 2931.00 MiB, V (f16): 2931.00 MiB
llama_init_from_model: CUDA_Host output buffer size = 0.95 MiB
llama_init_from_model: CUDA0 compute buffer size = 7763.94 MiB
llama_init_from_model: CUDA_Host compute buffer size = 3957.29 MiB
llama_init_from_model: graph nodes = 3137
llama_init_from_model: graph splits = 98
llama_init_from_model: enabling only_active_experts scheduling

main: n_kv_max = 250112, n_batch = 8096, n_ubatch = 8096, flash_attn = 1, n_gpu_layers = 99, n_threads = 101, n_threads_batch = 101

PP	TG	N_KV	T_PP s	S_PP t/s	T_TG s	S_TG t/s
8096	2024	0	3.155	2565.69	41.277	49.04
8096	2024	8096	3.215	2518.47	42.045	48.14
8096	2024	16192	3.320	2438.25	42.695	47.41
8096	2024	24288	3.433	2358.19	44.400	45.59
8096	2024	32384	3.543	2285.07	44.800	45.18

shewin

Apr 10

Not top-tier, but fast and quite usable.

ubergarm

Owner Apr 10

Yes, this quant is my "daily driver" full offload onto 2x A6000 GPUs (the older ones with 48GB VRAM each similar to 3090s).

It is the first local model that to me was "good enough" and "fast enough" for experimenting with opencode for local vibe coding, basic web stuff, etc. It is actually useful and saves me time from 'grep'ing all the code myself for a quick explanation etc.

I agree though, it is noticeably worse and makes more mistakes than big GLM-5.1, but as you mention, that one slows down quite a bit with long context and no -sm graph support.

dehnhaide

Apr 10

Yes, this quant is my "daily driver" full offload onto 2x A6000 GPUs (the older ones with 48GB VRAM each similar to 3090s).

How about the 397B version?! I found that to be my daily driver since it fits very well on 8x3090 with minimal RAM spill. It definitely not GLM5.1 but not far at all...

ubergarm

Owner Apr 10

@dehnhaide

I don't have enough VRAM to fully offload a reasonable 397B quant! 😛

I'm now experimenting with opencode to setup two agents, one for fast stuff (grepping and researching), and one for slow but more important stuff (writing code out)...

The config feels loosy goosey still though... too many files and options in different places.. maybe a .opencode only to keep it all in one place per project?

One night i'd love to leave a "ralph loop" running e.g. while true;do cat PROMPT.md | opencode run -;done haha.. see what monster is there in the morning, assuming i've got a kind of benchmark for it to optimize..

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment