Instructions to use ressl/gemma-4-31B-it-uncensored-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 ressl/gemma-4-31B-it-uncensored-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 ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ressl/gemma-4-31B-it-uncensored-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 ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ressl/gemma-4-31B-it-uncensored-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 ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ressl/gemma-4-31B-it-uncensored-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 ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ressl/gemma-4-31B-it-uncensored-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M

Ollama
How to use ressl/gemma-4-31B-it-uncensored-GGUF with Ollama:
```
ollama run hf.co/ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M
```
Unsloth Desktop

How to use ressl/gemma-4-31B-it-uncensored-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ressl/gemma-4-31B-it-uncensored-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": "ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ressl/gemma-4-31B-it-uncensored-GGUF with Docker Model Runner:
```
docker model run hf.co/ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M
```

Lemonade

How to use ressl/gemma-4-31B-it-uncensored-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-31B-it-uncensored-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ressl/gemma-4-31B-it-uncensored-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 ressl/gemma-4-31B-it-uncensored-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 ressl/gemma-4-31B-it-uncensored-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ressl/gemma-4-31B-it-uncensored-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ressl/gemma-4-31B-it-uncensored-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 "ressl/gemma-4-31B-it-uncensored-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"

gemma-4-31B-it-uncensored (GGUF)

GGUF K-quant ladder of ressl/gemma-4-31B-it-uncensored for llama.cpp, Ollama, and LM Studio. Uncensored: 0-1/100 effective refusals at every quant level (the uncensoring survives quantization down to 2-bit).

⚠️ Genuinely uncensored, it will comply with requests a stock model refuses.

Intended use, the constructive side. A non-refusing assistant is genuinely useful for ethical hacking, security research, and penetration testing: red-teaming, analyzing malware and exploit code, writing detection/YARA rules, reviewing vulnerabilities, and studying attack techniques without the model bailing out mid-task. Use it lawfully and responsibly.

ℹ️ gemma-4 has a thinking mode. llama.cpp enables it by default, so the answer lands in reasoning_content and content can look empty. For direct answers pass --reasoning-budget 0 (llama-server) or disable thinking in your client.

Format set

Repository	Format	Runs on
ressl/gemma-4-31B-it-uncensored	Transformers BF16, multimodal	transformers, vLLM, SGLang
ressl/gemma-4-31B-it-uncensored-NVFP4	NVIDIA NVFP4, multimodal	vLLM, SGLang on Blackwell
ressl/gemma-4-31B-it-uncensored-GGUF	GGUF q8_0 to q2_k, text only	llama.cpp, Ollama, LM Studio
ressl/gemma-4-31B-it-uncensored-MLX-bf16	MLX BF16, multimodal	mlx-vlm on Apple silicon
ressl/gemma-4-31B-it-uncensored-MLX-8bit	MLX 8-bit, multimodal	mlx-vlm on Apple silicon
ressl/gemma-4-31B-it-uncensored-MLX-6bit	MLX 6-bit, multimodal	mlx-vlm on Apple silicon
ressl/gemma-4-31B-it-uncensored-MLX-5bit	MLX 5-bit, multimodal	mlx-vlm on Apple silicon
ressl/gemma-4-31B-it-uncensored-MLX-4bit	MLX 4-bit, multimodal	mlx-vlm on Apple silicon

Quants

Text-only (llama.cpp drops the vision tower, the BF16/NVFP4 repos keep multimodal).

File	Size	Use when
`…-q8_0.gguf`	31 GB	maximum quality
`…-q6_k.gguf`	24 GB	near-lossless, smaller
`…-q5_k_m.gguf`	21 GB	high quality
`…-q4_k_m.gguf`	18 GB	recommended default, best size/quality
`…-q3_k_m.gguf`	15 GB	tight VRAM
`…-q2_k.gguf`	12 GB	smallest; still 0/100 uncensored, some quality loss

For full precision use the BF16 repo (an f16 GGUF exceeds Hugging Face's 50 GB per-file limit and is not hosted here).

All measured at 0/100 hard refusals except q5_k_m (1/100). GPU inference ~75 tok/s (q4, one RTX PRO 6000).

Run it with llama.cpp

llama-server -m gemma-4-31B-it-uncensored-biproj-q4_k_m.gguf \
  -ngl 99 -c 8192 --reasoning-budget 0

Run it with Ollama

# Modelfile:  FROM ./gemma-4-31B-it-uncensored-biproj-q4_k_m.gguf
ollama create gemma4-unc -f Modelfile && ollama run gemma4-unc

Needs a recent llama.cpp/Ollama build with Gemma4 GGUF support (build ≥ 2026-06).

Facts & figures


Base	ressl/gemma-4-31B-it-uncensored → google/gemma-4-31B-it
Type	uncensored (abliterated) build, 0/686 effective refusals across 4 datasets
Converter	llama.cpp `convert_hf_to_gguf.py` + `llama-quantize`

Cross-dataset validation

Generalization tested across 686 prompts from 4 independent datasets, 0 effective refusals everywhere:

Dataset	Prompts	Effective refusals
JailbreakBench	100	0/100
tulu-harmbench	320	0/320
NousResearch/RefusalDataset	166	0/166
mlabonne/harmful_behaviors	100	0/100
Total	686	0/686 (0.0%)

A naive keyword detector flags 363/686 (52.9%), every one is a ***Disclaimer:**-prefixed compliant answer, not a refusal. (Measured on the shared abliterated weights.)

❤️ Support

Producing and validating this complete format set (BF16 + NVFP4 + a full GGUF ladder, across vLLM, SGLang and llama.cpp on bleeding-edge Blackwell hardware) was a lot of work. If it's useful to you, I'd genuinely appreciate your support on Patreon 🙏, more at ressl.ch.

License & credits

Apache License 2.0, inherited from the base model by Google. See the official Gemma 4 license page. Uncensoring, format set and validation by Robert Ressl (Hugging Face · Website · LinkedIn · Patreon).

Downloads last month: 1,679

GGUF

Model size

31B params

Architecture

gemma4

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for ressl/gemma-4-31B-it-uncensored-GGUF

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Finetuned

ressl/gemma-4-31B-it-uncensored

Quantized

(7)

this model