Instructions to use magiccodingman/Granite-4.0-H-350M-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/Granite-4.0-H-350M-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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

Use Docker

docker model run hf.co/magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use magiccodingman/Granite-4.0-H-350M-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/Granite-4.0-H-350M-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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

Ollama
How to use magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF with Ollama:
```
ollama run hf.co/magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0
```

Unsloth Studio

How to use magiccodingman/Granite-4.0-H-350M-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/Granite-4.0-H-350M-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/Granite-4.0-H-350M-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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF to start chatting

How to use magiccodingman/Granite-4.0-H-350M-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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF with Docker Model Runner:
```
docker model run hf.co/magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0
```

Lemonade

How to use magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

Run and chat with the model

lemonade run user.Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use magiccodingman/Granite-4.0-H-350M-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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use magiccodingman/Granite-4.0-H-350M-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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0

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/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF:Q8_0" \
  --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"

Good work.

by BingoBird - opened Dec 22, 2025

Discussion

BingoBird

Dec 22, 2025

•

edited Dec 22, 2025

I want to signify my appreciation for your work and exploration into non-uniform quantization.

I can't provide informative feedback. I'm not qualified to evaluate the claims. But they sure sound sensible to me!

Do mxp4 ggufs make any sense (vs Q4_*) on hardware without native FP4 support?

Alright running the 580MB version in a live chat with several people and it's very fun. Terse. 29t/s generation on an old ryzen2 laptop. Vega8 Vulkan or CPU speed almost identical.

thanks! amazing!

magiccodingman

Owner Dec 28, 2025

Sorry for the late response, the holidays had me busy!

As for your questions on MXFP4 GGUFs vs Q4. So, native support for things like FP4 is obviously fantastic, but most of us don't have that support since true native FP4 support is really only native to high end Nvidia GPU's I believe right now. Basically, if your GPU doesn’t natively support something like FP4, it’s still handled correctly via dequantization and kernels, just not through true native FP4 hardware instructions. This has a small overhead cost, but I'd pretty confidently guess that 99% of the time, it never really matters for the majority of people. Plus, I'm subscribed to the philosophy of not just posting a model, but the benchmarks because I want to trust the data, not the vibes.

I'll hopefully have updates for this model potentially in the near future as well. This 350M model is really easy for me to work with when testing. I've got a whole new architecture I'm brewing for MagicQuant. Now I'm unsure if the new architecture will find anything better for this model specifically, but the new MagicQuant code hopefully will make even more fun mixes.

But I'm glad enjoy the project and this model! I was hoping someone would enjoy the near lossless 350M model because it was a hard quant mix to find! These tiny models cannot take a 1% to 5% PPL delta % loss like larger models can, it's way more sensitive.

Thanks again, I'm glad you enjoy it!

floory

Dec 29, 2025

i really enjoyed testing out your quants - when are new releases coming? i keep checking every few days but you've not posted in 3 weeks ;(

magiccodingman

Owner Dec 30, 2025

I can only do this on the side, so I don't have a hard deadline yet. But I'm hoping mid to late January and hopefully at most sometime in February.

magiccodingman changed discussion status to closed Dec 30, 2025

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