Instructions to use RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF",
	filename="Qwen3.6-35B-A3B-IQ4_KS.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RDson/Qwen3.6-35B-A3B-IQ4_KS-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 RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF
# Run inference directly in the terminal:
llama cli -hf RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF
# Run inference directly in the terminal:
llama cli -hf RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

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 RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF
# Run inference directly in the terminal:
./llama-cli -hf RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

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 RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

Use Docker

docker model run hf.co/RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

LM Studio
Jan

vLLM

How to use RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RDson/Qwen3.6-35B-A3B-IQ4_KS-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": "RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

Ollama
How to use RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF with Ollama:
```
ollama run hf.co/RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF
```

Unsloth Studio

How to use RDson/Qwen3.6-35B-A3B-IQ4_KS-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 RDson/Qwen3.6-35B-A3B-IQ4_KS-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 RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF to start chatting

How to use RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

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": "RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use RDson/Qwen3.6-35B-A3B-IQ4_KS-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 RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

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 RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF with Docker Model Runner:
```
docker model run hf.co/RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF
```

Lemonade

How to use RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-IQ4_KS-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Qwen3.6-35B-A3B IQ4_KS GGUF

ik_llama.cpp is required to run this model.

ik_llama.cpp imatrix quantization of Qwen/Qwen3.6-35B-A3B.

This quant uses a mixed-precision recipe to maximize quality while fitting entirely into 24GB VRAM for full GPU offloading. Attention, SSM, and shared expert layers are kept at Q8_0/F32, while the massive routed MoE expert layers are quantized to IQ5_KS and IQ4_KS.

Perplexity

Measured against wiki.test.raw with n_ctx=512:

Quant	Size	PPL
IQ4_KS	~19.8 GiB	6.7401 +/- 0.04381

*Note: Lower is better.

Quantization Recipe

The "Secret Recipe" used for the mixed-precision tensor overrides is based on the methodology used by ubergarm:

custom="
# 60 Repeating Layers [0-59]
## Gated Attention/Delta Net [Blended 0-59]
blk\..*\.attn_gate\.weight=q8_0
blk\..*\.attn_qkv\.weight=q8_0
blk\..*\.attn_output\.weight=q8_0
blk\..*\.attn_q\.weight=q8_0
blk\..*\.attn_k\.weight=q8_0
blk\..*\.attn_v\.weight=q8_0
blk\..*\.ssm_alpha\.weight=f32
blk\..*\.ssm_beta\.weight=f32
blk\..*\.ssm_out\.weight=q8_0
# Shared Expert Layers [0-59]
blk\..*\.ffn_down_shexp\.weight=q8_0
blk\..*\.ffn_(gate|up)_shexp\.weight=q8_0
# Routed Experts Layers [0-59]
blk\..*\.ffn_down_exps\.weight=iq5_ks
blk\..*\.ffn_(gate|up)_exps\.weight=iq4_ks
# Non-Repeating Layers
token_embd\.weight=q8_0
output\.weight=q8_0
"

custom=$(
  echo "$custom" | grep -v '^#' | \
  sed -Ez 's:\n+:,:g;s:,$::;s:^,::'
)

How This Was Made (Reproduction Steps)

Because generating an imatrix directly from a ~65GB BF16 model requires massive system RAM, we use a Q8_0 intermediate step to generate the imatrix without running out of memory.

1. Convert HF Safetensors to BF16 GGUF

python llama.cpp/convert_hf_to_gguf.py \
  --outtype bf16 \
  --split-max-size 50G \
  --outfile ./Qwen3.6-35B-A3B-BF16.gguf \
  /path/to/Qwen3.6-35B-A3B/

2. Quantize to Q8_0 (For Imatrix Generation)

./ik_llama.cpp/build/bin/llama-quantize \
  ./Qwen3.6-35B-A3B-BF16-00001-of-00002.gguf \
  ./Qwen3.6-35B-A3B-Q8_0.gguf \
  Q8_0 16

3. Generate the Imatrix Note: GGML_CUDA_NO_PINNED=1 is used to prevent system RAM exhaustion on 24GB VRAM setups.

GGML_CUDA_NO_PINNED=1 ./ik_llama.cpp/build/bin/llama-imatrix \
  -m ./Qwen3.6-35B-A3B-Q8_0.gguf \
  -f /path/to/ubergarm-imatrix-calibration-corpus-v02.txt \
  -o Qwen3.6-35B-A3B-imatrix.dat \
  --ctx-size 512 \
  -t 11 \
  --fit

4. Quantize BF16 to IQ4_KS We use the original BF16 model here with the Q8_0-generated imatrix for maximum fidelity.

./ik_llama.cpp/build/bin/llama-quantize \
  --imatrix ./Qwen3.6-35B-A3B-imatrix.dat \
  --custom-q "$custom" \
  ./Qwen3.6-35B-A3B-BF16-00001-of-00002.gguf \
  ./Qwen3.6-35B-A3B-IQ4_KS.gguf \
  IQ4_KS 16

5. Test Perplexity

wget https://huggingface.co/datasets/ikawrakow/validation-datasets-for-llama.cpp/resolve/main/wiki.test.raw.gz
gunzip wiki.test.raw.gz

./ik_llama.cpp/build/bin/llama-perplexity \
  -m ./Qwen3.6-35B-A3B-IQ4_KS.gguf \
  -f ./wiki.test.raw \
  -c 512 \
  -ngl 99 \
  -t 1 \
  -fa

Quick Start Inference

Requires ik_llama.cpp.

./ik_llama.cpp/build/bin/llama-server \
  -m ./Qwen3.6-35B-A3B-IQ4_KS.gguf \
  -c 131072 \
  -ngl 99

Downloads last month: 1,670

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

Model tree for RDson/Qwen3.6-35B-A3B-IQ4_KS-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(609)

this model