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.

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-GGUF",
	filename="granite-4.0-h-350m-unsloth-mxfp4_moe-EKUD-B16-O-Q6K-Q-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

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

Install from brew

brew install llama.cpp
# 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

Install from WinGet (Windows)

winget install llama.cpp
# 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

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 new

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

Pi new

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

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

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

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-server -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

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

MagicQuant GGUF Hybrids - granite 4.0 h 350m unsloth

(DEPRECIATED - Part of MagicQuant v1.0 which had significant flaws. Please utilize v2.0 which is production ready)

MagicQuant is an automated quantization, benchmarking, and evolutionary hybrid-GGUF search system for LLMs.

Each release includes models optimized to outperform standard baseline quants (Q8, Q6, Q5, Q4). If a baseline GGUF exists in this repo, the evolutionary engine couldn’t beat it. If a baseline is missing, it’s because a hybrid configuration outperformed it so completely that including the baseline would've been pointless.

These hybrid GGUFs are built to be as small, fast, and low-drift as possible while preserving model capability.

To dive deeper into how MagicQuant works, see the main repo: MagicQuant on GitHub (by MagicCodingMan)

Notes:

The HuggingFace hardware compatibility where it shows the bits is usually wrong. It doesn't understand hybrid mixes, so don't trust it.
Naming scheme can be found on the MagicQuant Wiki.
(tips) Less precision loss means less brain damage. More TPS means faster! Smaller is always better right?

Precision Loss Guide

0–0.1% → God-tier, scientifically exact
0.1–1% → True near-lossless, agent-ready
1–3% → Minimal loss, great for personal use
3–5% → Borderline, but still functional
5%+ → Toys, not tools, outside MagicQuant’s scope

Learn more about precision loss here.

IMPORTANT NOTE: Due to this model being so small. The test was significantly stricter in what precision loss was allowed.

Table - File Size + TPS + Avg Precision Loss

model_name	file_size_gb	bench_tps	avg_prec_loss
mxfp4_moe-EKUD-B16-O-Q6K-Q-Q8_0	0.54	1705.35	0.0816%
mxfp4_moe-O-Q6K-EQKUD-Q8_0	0.34	1605.97	0.2555%

Table - PPL Columns

model_name	gen	gen_er	code	code_er	math	math_er
mxfp4_moe-EKUD-B16-O-Q6K-Q-Q8_0	18.1560	0.4667	1.9548	0.0175	10.2986	0.2319
mxfp4_moe-O-Q6K-EQKUD-Q8_0	18.2304	0.4691	1.9555	0.0175	10.3074	0.2320

gen = ppl_general, code = ppl_code, math = ppl_math

Table - Precision Loss Columns

model_name	loss_general	loss_code	loss_math
mxfp4_moe-EKUD-B16-O-Q6K-Q-Q8_0	0.1368	0.0051	0.1030
mxfp4_moe-O-Q6K-EQKUD-Q8_0	0.5471	0.0307	0.1886

loss_* values are absolute precision-loss % vs BF16 per domain.

Baseline Models (Reference)

Table - File Size + TPS + Avg Precision Loss

model_name	file_size_gb	bench_tps	avg_prec_loss
BF16	0.64	1718.28	0.0000%
Q8_0	0.34	1598.28	0.3116%
Q6_K	0.26	1513.71	0.5598%
Q5_K	0.24	1305.37	2.8875%
Q4_K_M	0.21	1401.44	12.2733%
IQ4_NL	0.20	1679.00	14.2608%
MXFP4_MOE	0.17	1713.00	8222.4218%

Table - PPL Columns

model_name	gen	gen_er	code	code_er	math	math_er
BF16	18.1312	0.4655	1.9549	0.0175	10.2880	0.2315
Q8_0	18.2363	0.4693	1.9558	0.0175	10.3198	0.2325
Q6_K	18.3753	0.4719	1.9612	0.0175	10.2869	0.2294
Q5_K	18.9974	0.4899	1.9842	0.0180	10.5335	0.2365
Q4_K_M	21.5138	0.5690	2.0633	0.0194	11.5862	0.2686
IQ4_NL	22.4687	0.6035	2.0709	0.0194	11.6178	0.2686
MXFP4_MOE	1172.2706	45.9470	303.0942	7.7666	308.3771	10.9069

gen = ppl_general, code = ppl_code, math = ppl_math

Table - Precision Loss Columns

model_name	loss_general	loss_code	loss_math
BF16	0.0000	0.0000	0.0000
Q8_0	0.5797	0.0460	0.3091
Q6_K	1.3463	0.3223	0.0107
Q5_K	4.7774	1.4988	2.3863
Q4_K_M	18.6562	5.5450	12.6186
IQ4_NL	23.9229	5.9338	12.9257
MXFP4_MOE	6365.4882	15404.3327	2897.4446

loss_* values are absolute precision-loss % vs BF16 per domain.

Support

I’m a solo developer working full time for myself to achieve my dream, pouring nights and weekends into open protocols and tools that I hope make the world a little better. If you chip in, you're helping me keep the lights on while I keep shipping.

Click here to see ways to support - BTC, Paypal, GitHub sponsors.

Or, just drop a like on the repo :)