Instructions to use LakoMoor/QClaw-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use LakoMoor/QClaw-4B-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 LakoMoor/QClaw-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LakoMoor/QClaw-4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf LakoMoor/QClaw-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LakoMoor/QClaw-4B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf LakoMoor/QClaw-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf LakoMoor/QClaw-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LakoMoor/QClaw-4B-GGUF:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use LakoMoor/QClaw-4B-GGUF with Ollama:
```
ollama run hf.co/LakoMoor/QClaw-4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use LakoMoor/QClaw-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LakoMoor/QClaw-4B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "LakoMoor/QClaw-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use LakoMoor/QClaw-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/LakoMoor/QClaw-4B-GGUF:Q4_K_M
```

Lemonade

How to use LakoMoor/QClaw-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LakoMoor/QClaw-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.QClaw-4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use LakoMoor/QClaw-4B-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 LakoMoor/QClaw-4B-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 LakoMoor/QClaw-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LakoMoor/QClaw-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LakoMoor/QClaw-4B-GGUF:Q4_K_M

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 "LakoMoor/QClaw-4B-GGUF:Q4_K_M" \
  --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"

QClaw-4B-GGUF

QClaw-4B-GGUF is the quantized GGUF version of LakoMoor/QClaw-4B — a 4-billion parameter model fine-tuned for agentic tasks and tool use, designed for use with OpenClaw-compatible agent frameworks.

This repository provides GGUF files for local inference with llama.cpp, Ollama, LM Studio, Jan, and other compatible runtimes.

Available Quantizations

Filename	Quant	Size	Quality	Recommended
`QClaw-4B-F16.gguf`	F16	~8 GB	Maximum	Servers / high VRAM
`QClaw-4B-Q8_0.gguf`	Q8_0	~4.5 GB	Excellent	High quality inference
`QClaw-4B-Q5_K_M.gguf`	Q5_K_M	~3 GB	Very good	⭐ Best balance
`QClaw-4B-Q4_K_M.gguf`	Q4_K_M	~2.5 GB	Good	⭐ Most popular
`QClaw-4B-Q3_K_M.gguf`	Q3_K_M	~2 GB	Medium	Low RAM devices

Usage

llama.cpp

./llama-server \
  -m QClaw-4B-Q4_K_M.gguf \
  -a qclaw-4b \
  --jinja \
  --port 8000

Ollama

ollama run hf.co/LakoMoor/QClaw-4B-GGUF:Q4_K_M

LM Studio

Search for LakoMoor/QClaw-4B-GGUF in the model browser and select your preferred quantization.

Model Details

Base model: LakoMoor/QClaw-4B
Architecture: Decoder-only transformer (Qwen3.5-4B based)
Parameters: ~4B
Quantization tool: llama.cpp
Primary use case: Agentic workflows, tool calling, multi-step reasoning

Intended Use

QClaw-4B-GGUF is intended for:

Local inference on consumer hardware (CPU and GPU)
Agentic pipelines using OpenClaw or compatible frameworks
Tool-augmented assistants requiring compact, efficient inference
Research into small-model agent capabilities

Out-of-scope use: Not intended for safety-critical systems without additional alignment work.

Training annotation cards and dataset curation provided by Aleksandr Nikolich — Love. Death. Transformers..

Citation

@misc{qclaw4b2026,
  title  = {QClaw-4B: State-of-the-Art 4B Agent Model for OpenClaw},
  author = {Nikolay Kompanets (LakoMoor)},
  year   = {2026},
  url    = {https://huggingface.co/LakoMoor/QClaw-4B}
}

License

Apache 2.0

Downloads last month: 311

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

8-bit

16-bit

32-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for LakoMoor/QClaw-4B-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

LakoMoor/QClaw-4B

Quantized

(5)

this model

Evaluation results

Overall Score
self-reported

84.800
Pass Rate (%)
self-reported

73.500