Instructions to use steampunque/Qwen3-4B-MP-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 steampunque/Qwen3-4B-MP-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 steampunque/Qwen3-4B-MP-GGUF:Q8_0_H
# Run inference directly in the terminal:
llama cli -hf steampunque/Qwen3-4B-MP-GGUF:Q8_0_H

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf steampunque/Qwen3-4B-MP-GGUF:Q8_0_H
# Run inference directly in the terminal:
llama cli -hf steampunque/Qwen3-4B-MP-GGUF:Q8_0_H

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 steampunque/Qwen3-4B-MP-GGUF:Q8_0_H
# Run inference directly in the terminal:
./llama-cli -hf steampunque/Qwen3-4B-MP-GGUF:Q8_0_H

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 steampunque/Qwen3-4B-MP-GGUF:Q8_0_H
# Run inference directly in the terminal:
./build/bin/llama-cli -hf steampunque/Qwen3-4B-MP-GGUF:Q8_0_H

Use Docker

docker model run hf.co/steampunque/Qwen3-4B-MP-GGUF:Q8_0_H

LM Studio
Jan
Ollama
How to use steampunque/Qwen3-4B-MP-GGUF with Ollama:
```
ollama run hf.co/steampunque/Qwen3-4B-MP-GGUF:Q8_0_H
```

Unsloth Studio

How to use steampunque/Qwen3-4B-MP-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 steampunque/Qwen3-4B-MP-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 steampunque/Qwen3-4B-MP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for steampunque/Qwen3-4B-MP-GGUF to start chatting

How to use steampunque/Qwen3-4B-MP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf steampunque/Qwen3-4B-MP-GGUF:Q8_0_H

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": "steampunque/Qwen3-4B-MP-GGUF:Q8_0_H"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use steampunque/Qwen3-4B-MP-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 steampunque/Qwen3-4B-MP-GGUF:Q8_0_H

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 steampunque/Qwen3-4B-MP-GGUF:Q8_0_H

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use steampunque/Qwen3-4B-MP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf steampunque/Qwen3-4B-MP-GGUF:Q8_0_H

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 "steampunque/Qwen3-4B-MP-GGUF:Q8_0_H" \
  --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 steampunque/Qwen3-4B-MP-GGUF with Docker Model Runner:
```
docker model run hf.co/steampunque/Qwen3-4B-MP-GGUF:Q8_0_H
```

Lemonade

How to use steampunque/Qwen3-4B-MP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull steampunque/Qwen3-4B-MP-GGUF:Q8_0_H

Run and chat with the model

lemonade run user.Qwen3-4B-MP-GGUF-Q8_0_H

List all available models

lemonade list

Mixed Precision GGUF layer quantization of Qwen3-4B by Alibaba

Original model: https://huggingface.co/Qwen/Qwen3-4B

The hybrid quant employs different quantization levels on a per layer basis to increased flexibility of trading off performance vs file size. Less parameter bits are used at deep layers and more bits at cortex layers to simultaneously optimize quantized size and model performance. These quants were specifically optimized for the Qwen3 4B edge model for essentially no performance loss vs Q8_0 quant while reducing file size about 0.6G.

The layer quants are as follows:

   LAYER_TYPES='[
   [0 ,"Q8_0"  ],[1 ,"Q5_K_M"],[2 ,"Q5_K_M"],[3 ,"Q5_K_M"],[4 ,"Q5_K_M"],[5 ,"Q5_K_M"],
   [6 ,"Q5_K_M"],[7 ,"Q5_K_M"],[8, "Q5_K_M"],[9, "Q5_K_M"],[10,"Q5_K_M"],[11,"Q5_K_M"],
   [12,"Q6_K"  ],[13,"Q6_K"  ],[14,"Q6_K"  ],[15,"Q6_K"  ],[16,"Q6_K"  ],[17,"Q6_K"  ],
   [18,"Q6_K"  ],[19,"Q6_K"  ],[20,"Q6_K"  ],[21,"Q6_K"  ],[22,"Q6_K"  ],[23,"Q6_K"  ],
   [24,"Q8_0"  ],[25,"Q8_0"  ],[26,"Q8_0"  ],[27,"Q8_0"  ],[28,"Q8_0"  ],[29,"Q8_0"  ],
   [30,"Q8_0"  ],[31,"Q8_0"  ],[32,"Q8_0"  ],[33,"Q8_0"  ],[34,"Q8_0"  ],[35,"Q8_0"  ]
   ]'
   FLAGS="--token-embedding-type Q8_0 --output-tensor-type Q6_K"

These quants were select based on combined subjective and objective performance evaluations to give both high performance and reduced file size.

Comparison:

Quant	size	PPL	Comment
Q8_0	4.3e9	13.2	default embed and output
Q8_0_H	3.6e9	13.1	Q8_0 embed Q6_K output

Full evals comparing Qwen3 4B Q8_0 and Q8_0_H are also available at https://huggingface.co/spaces/steampunque/benchlm

Download the file from below:

Link	Type	Size/e9 B	Notes
Qwen3-4B.Q8_0_H.gguf	Q8_0_H	3.6e9 B	Q8_0 quality

A discussion thread about the hybrid layer quant approach can be found here on the llama.cpp git repository:

https://github.com/ggml-org/llama.cpp/discussions/13040

Downloads last month: 20

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for steampunque/Qwen3-4B-MP-GGUF

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(277)

this model