Instructions to use douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF",
	filename="gemma-4-31b-jang-crack-Q3_K_M.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 douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf douyamv/Gemma-4-31B-JANG_4M-CRACK-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 douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf douyamv/Gemma-4-31B-JANG_4M-CRACK-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 douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M

Use Docker

docker model run hf.co/douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "douyamv/Gemma-4-31B-JANG_4M-CRACK-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": "douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M

Ollama
How to use douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF with Ollama:
```
ollama run hf.co/douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M
```

Unsloth Studio new

How to use douyamv/Gemma-4-31B-JANG_4M-CRACK-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 douyamv/Gemma-4-31B-JANG_4M-CRACK-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 douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF to start chatting

Pi new

How to use douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M

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": "douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use douyamv/Gemma-4-31B-JANG_4M-CRACK-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 douyamv/Gemma-4-31B-JANG_4M-CRACK-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 douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF with Docker Model Runner:
```
docker model run hf.co/douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M
```

Lemonade

How to use douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-31B-JANG_4M-CRACK-GGUF-Q4_K_M

List all available models

lemonade list

Gemma-4-31B-JANG_4M-CRACK-GGUF

GGUF quantizations of Gemma-4-31B-JANG_4M-CRACK for use with llama.cpp, LM Studio, Ollama, and other GGUF-compatible inference engines.

About the Model

Base model: google/gemma-4-31b-it
Architecture: Gemma 4 Dense Transformer (31B parameters, 60 layers)
Features: Hybrid Sliding/Global Attention, Vision + Audio multimodal
Modification: CRACK abliteration (refusal removal) + JANG v2 mixed-precision quantization

Why This Conversion?

The original model uses JANG v2 mixed-precision MLX quantization (attention 8-bit + MLP 4-bit), which is only compatible with vMLX. Standard tools (llama.cpp, LM Studio, oMLX, mlx-lm) cannot load this format due to mixed per-layer bit widths.

This repository provides standard GGUF quantizations that work everywhere.

Conversion Process

Original (JANG v2 MLX safetensors, ~18GB)
    ↓ dequantize (attention 8-bit → f16, MLP 4-bit → f16)
Intermediate (float16 safetensors, ~60GB)
    ↓ convert_hf_to_gguf.py + quantize
GGUF (various quantizations)

Note: Since the original was already quantized (avg 5.1 bits), the dequantized f16 intermediate is an approximation. Re-quantizing to GGUF introduces minimal additional quality loss since the attention layers were preserved at 8-bit in the original.

Available Quantizations

File	Quant	Size	Quality	Notes
`gemma-4-31b-jang-crack-Q3_K_M.gguf`	Q3_K_M	~14 GB	Acceptable	Minimum viable quality
`gemma-4-31b-jang-crack-Q4_K_M.gguf`	Q4_K_M	~18 GB	Good	Best size/quality balance
`gemma-4-31b-jang-crack-Q5_K_M.gguf`	Q5_K_M	~21 GB	Better	Recommended if RAM allows
`gemma-4-31b-jang-crack-Q6_K.gguf`	Q6_K	~25 GB	Very Good	High quality
`gemma-4-31b-jang-crack-Q8_0.gguf`	Q8_0	~33 GB	Near lossless	Closest to original

System Requirements

Quantization	Minimum RAM	Recommended
Q3_K_M	20 GB	24 GB
Q4_K_M	24 GB	32 GB
Q5_K_M	28 GB	36 GB
Q6_K	32 GB	40 GB
Q8_0	40 GB	48 GB

Usage

LM Studio

Download any .gguf file and open it in LM Studio.

llama.cpp

./llama-cli -m gemma-4-31b-jang-crack-Q4_K_M.gguf -p "Hello" -n 256

Ollama

echo 'FROM ./gemma-4-31b-jang-crack-Q4_K_M.gguf' > Modelfile
ollama create gemma4-crack -f Modelfile
ollama run gemma4-crack

License

Gemma License

Disclaimer

This model has had safety guardrails removed. Use responsibly and in compliance with applicable laws.

Downloads last month: 64,509

GGUF

Model size

31B params

Architecture

gemma4

Hardware compatibility

3-bit

4-bit

8-bit

douyamv
/

Gemma-4-31B-JANG_4M-CRACK-GGUF

Gemma-4-31B-JANG_4M-CRACK-GGUF

About the Model

Why This Conversion?

Conversion Process

Available Quantizations

System Requirements

Usage

LM Studio

llama.cpp

Ollama

License

Disclaimer

Space using douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF 1