Instructions to use rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF",
	filename="qwen36-a3b-claude-coder-q4_K_M-llama.cpp.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 rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M

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 rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M

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 rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M

Use Docker

docker model run hf.co/rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rafw007/qwen36-a3b-claude-coder-llama.cpp-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": "rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M

Ollama
How to use rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF with Ollama:
```
ollama run hf.co/rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M
```

Unsloth Studio

How to use rafw007/qwen36-a3b-claude-coder-llama.cpp-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 rafw007/qwen36-a3b-claude-coder-llama.cpp-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 rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF to start chatting

How to use rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M

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": "rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use rafw007/qwen36-a3b-claude-coder-llama.cpp-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 rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M

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 rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF with Docker Model Runner:
```
docker model run hf.co/rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M
```

Lemonade

How to use rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.qwen36-a3b-claude-coder-llama.cpp-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.6 Claude Coder — local MoE coding agent (llama.cpp build)

A custom configuration of Qwen3.6-35B-A3B (Mixture-of-Experts, ~3B active parameters), set up to act as an autonomous coding agent: it uses tools instead of guessing, grounds every answer in the actual tool output (never fabricates results), does not loop on the same tool, and returns complete, runnable code. No-think mode is wired into the system prompt for fast, direct answers. Safety guardrails of the base model are intact.

It drives Claude Code, Codex and opencode fully locally — your code never leaves your machine and cloud token cost drops to zero.

This is the llama.cpp / ik_llama.cpp build. Same behavior and configuration as rafw007/qwen36-a3b-claude-coder on Ollama — packaged so it loads on stock llama.cpp. See "Why a separate version" below.

Why a separate version (vs. the Ollama one)

The Ollama model and this one share the same agent config (system prompt + sampling params). What differs is packaging and the loader they target:

	Ollama version	This llama.cpp version
Runtime	Ollama engine + Modelfile (`RENDERER`/`PARSER qwen3.5`)	stock `llama.cpp` / `ik_llama.cpp` (`llama-server`)
Weights	nvfp4 (~21 GB)	GGUF Q4_K_M (~24 GB)
Tool format	Ollama's native Qwen parser	GGUF Jinja chat template + `--jinja`
Agent config	baked into the Modelfile	supplied via launch flags + a system-prompt file (below)

The actual fix. Qwen3.5/3.6-MoE uses multimodal RoPE (mRoPE) whose native rope.dimension_sections is 3 ints [t, h, w]. Ollama's loader is lenient and accepts that. Recent stock llama.cpp (the Qwen3.5 loader from PR #19435) validates that key as a length-4 array and rejects the 3-element one:

key qwen35moe.rope.dimension_sections has wrong array length; expected 4, got 3

This is a known, family-wide converter/loader mismatch — not specific to this quant. This GGUF has the section array padded to length 4 ([11, 11, 10] → [11, 11, 10, 0]; the 4th slot is the unused text section, it does not change inference), so it loads cleanly on current llama.cpp and ik_llama.cpp. If you hit the error above with any other Qwen3.5/3.6-MoE GGUF, this is the cause.

What it is (and what it is not)

Honest framing: the weights are stock Qwen3.6-35B-A3B. The "Claude Coder" behavior comes entirely from an agentic system prompt + sampling configuration, plus the llama.cpp-compatibility rope fix described above. Everything here is measured, not marketing.

Quick start (llama.cpp / ik_llama.cpp)

llama-server \
  -m qwen36-a3b-claude-coder-q4_K_M-llama.cpp.gguf \
  --jinja --reasoning-budget 0 \
  -c 65536 \
  --temp 0.6 --top-k 20 --top-p 0.8 --repeat-penalty 1 --presence-penalty 0 \
  --system-prompt-file qwen36-system.txt \
  --host 0.0.0.0 --port 8080

--reasoning-budget 0 enforces no-think. --jinja enables native tool-calling via the embedded Qwen chat template. qwen36-system.txt is your agent system-prompt file (same configuration as the Ollama build — its contents are not published).

Tested

End-to-end under opencode against ik_llama.cpp (llama-server, port-bound, --jinja): the model emitted real tool_calls, executed a real df -h, grounded its answer on the actual output and exited cleanly (no tool loop). Loads without the rope error on ik_llama.cpp (mRoPE sections reported as [11, 11, 10, 0]).

Context

Configured for 64K (Claude Code's recommended minimum). Base Qwen3.6 natively supports 262K, so context can be raised on stronger hardware. On a CPU-only box lower it (e.g. 16–32K) to fit RAM.

Files

File	Quant	Size	Notes
`qwen36-a3b-claude-coder-q4_K_M-llama.cpp.gguf`	Q4_K_M	~24 GB	mRoPE `dimension_sections` padded to length-4 for stock llama.cpp / ik_llama.cpp.

How it was made

Designed, built and tested with the help of Claude Opus — the system prompt, parameter choices and context configuration come from that work. The llama.cpp packaging (rope-section fix + launch recipe) was added after a user report that the Ollama-targeted GGUF would not load on stock llama.cpp.

License

Apache 2.0 (inherited from the base Qwen3.6).

Downloads last month: 70

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for rafw007/qwen36-a3b-claude-coder-llama.cpp-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(452)

this model