Instructions to use magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-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 magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-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 magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

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 magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL
# Run inference directly in the terminal:
./llama-cli -hf magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

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 magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

Use Docker

docker model run hf.co/magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

LM Studio
Jan

vLLM

How to use magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-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": "magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

Ollama
How to use magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF with Ollama:
```
ollama run hf.co/magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL
```

Unsloth Studio

How to use magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-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 magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-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 magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF to start chatting

How to use magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

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": "magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF with Docker Model Runner:
```
docker model run hf.co/magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL
```

Lemonade

How to use magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

Run and chat with the model

lemonade run user.Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF-IQ4_NL

List all available models

lemonade list

Hermes Agent

How to use magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-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 magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

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 magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL

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 "magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF:IQ4_NL" \
  --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"

Any chance for Qwen3-VL-4B-Instruct with MagicQuant MXFP4 GGUF?

by ampersandru - opened Jan 20

Discussion

ampersandru

Jan 20

Saw llama.cpp recently merged MXFP4 support, and was extremely excited to see this model, but realized it doesn't have VL. Any chance this can be done?

Thanks for all your work!

magiccodingman

Owner Jan 21

That's a good one to add to the list for me to run through the MagicQuant process :D I'm a bit behind at the moment with lots of things so I'm kinda of backed up, so my open source work is delayed. Lots of work + dealing with a loss/grief as of early this year.

But I'm getting back on my feet. I likely need to find a good vision benchmark though because I'm unsure how this process affects vision in general. And that's something I need to really play with and make sure I protect.

But on the good news, before I fell a bit off the wagon, the new code base I'm making if my current hypothesis works out, I should be able to do some pretty cool stuff and get some great quantized versions out!

ampersandru

Jan 21

Thanks for your response! Really sorry about your loss, definitely take care of yourself first - AI and projects later! Im curious how MXFP4 affects vision as well - but Im assuming it will still use a separate MMPROJ?

jerkar

Jan 24

Very glad to see you back. Have had very good results from your prior work.

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