Instructions to use unsloth/gemma-4-12B-it-qat-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/gemma-4-12B-it-qat-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/gemma-4-12B-it-qat-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/gemma-4-12B-it-qat-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/gemma-4-12B-it-qat-GGUF",
	filename="MTP/gemma-4-12B-it-BF16-MTP.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/gemma-4-12B-it-qat-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 unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL

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 unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL

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 unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use unsloth/gemma-4-12B-it-qat-GGUF with Ollama:
```
ollama run hf.co/unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/gemma-4-12B-it-qat-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 unsloth/gemma-4-12B-it-qat-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 unsloth/gemma-4-12B-it-qat-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/gemma-4-12B-it-qat-GGUF to start chatting

How to use unsloth/gemma-4-12B-it-qat-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL

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": "unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/gemma-4-12B-it-qat-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 unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL

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 unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use unsloth/gemma-4-12B-it-qat-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/gemma-4-12B-it-qat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/gemma-4-12B-it-qat-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.gemma-4-12B-it-qat-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Gemma-4 QAT Special Unsloth quants

by danielhanchen - opened 19 days ago

Discussion

danielhanchen

Unsloth AI org 19 days ago

Hey folks! We converted Gemma-4 QAT quants in a different way since a direct llama.cpp Q4_0 loses accuracy when converting from BF16 QAT directly.

E2B for example has a mean KLD of 0.00173 vs 0.05109 (29x better relatively) for a naive Q4_0 quantization, and ours is even 22% smaller!

See https://unsloth.ai/docs/models/gemma-4/qat#qat-analysis

jian2023

19 days ago

Does it support MTP? Please provide more examples.

HobbledBacon

18 days ago

This comment has been hidden

JeanLima2024

18 days ago

Use o mmproj-F32.gguf aqui do modelo funcionou aqui usando o Llama.cpp, funcionando com imagens.

HobbledBacon

18 days ago

This comment has been hidden

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