Instructions to use magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-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-MXFP4-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-MXFP4-Hybrid-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-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 magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-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 magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-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 magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M

Use Docker

docker model run hf.co/magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-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-MXFP4-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-MXFP4-Hybrid-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M

Ollama
How to use magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF with Ollama:
```
ollama run hf.co/magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M
```

Unsloth Studio

How to use magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-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-MXFP4-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-MXFP4-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-MXFP4-Hybrid-GGUF to start chatting

How to use magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-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-MXFP4-Hybrid-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": "magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF with Docker Model Runner:
```
docker model run hf.co/magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M
```

Lemonade

How to use magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-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-MXFP4-Hybrid-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 magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-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-MXFP4-Hybrid-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 "magiccodingman/Qwen3-4B-Instruct-2507-MXFP4-Hybrid-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"

magiccodingman commited on Dec 3, 2025

Commit

3ec697e

verified ·

1 Parent(s): 26fb4e2

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -0

README.md CHANGED Viewed

@@ -13,6 +13,16 @@ tags:
 - qwen3
 - mxfp4_hybrid
 ---
 # Qwen3 4B Instruct 2507 MXFP4 Hybrid GGUF
 **Dense model utilizing MXFP4_MOE with hybrid weights on a dense model. Achieving interesting results that show smaller file size, more TPS, and near lossless precision.**

 - qwen3
 - mxfp4_hybrid
 ---
+# DEPRECIATED!
+This model was surpassed by:
+https://huggingface.co/magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUFF
+Use the new version. This shown MXFP4 hybrid is no longer viable in comparison, nor really useable. The data collected is good for understanding and research, but it's not as good for real use.
 # Qwen3 4B Instruct 2507 MXFP4 Hybrid GGUF
 **Dense model utilizing MXFP4_MOE with hybrid weights on a dense model. Achieving interesting results that show smaller file size, more TPS, and near lossless precision.**