Gemma-4-E4B-Uncensored-Genesis-GGUF

Instructions to use LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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 LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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 LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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 LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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 LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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 LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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": "LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M

Ollama
How to use LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF with Ollama:
```
ollama run hf.co/LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M
```
Unsloth Desktop

How to use LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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": "LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF with Docker Model Runner:
```
docker model run hf.co/LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M
```

Lemonade

How to use LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-E4B-Uncensored-Genesis-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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 LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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 LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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 "LuffyTheFox/Gemma-4-E4B-Uncensored-Genesis-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-E4B-Uncensored-HauhauCS-Aggressive -> Genesis

⚡ Why Genesis project exists? During training, ALL models don't just learn knowledge - they also accumulate random noise in their tensors. This noise builds up and creates something I call the Noise Gate - a fundamental barrier that stops LLM models from learning further and makes them unstable, verbose, and prone to hallucinations. My approach reduces this noise. It repairs the signal without touching the learned knowledge and gradient. The result is a model that consistent in performance, context clarity and following instructions, because it's no longer fighting its own internal chaos.

This is Gemma-4-E4B-Uncensored-HauhauCS-Aggressive model. made by HauhauCS

upgraded via Genesis training noise distillation algorythm made by me.

Vision encoder is not included because it's unfixable and broken too much. Here stats.txt

Join the Discord for updates, roadmaps, projects, or just to chat.

HuggingFace's "Hardware Compatibility" widget doesn't recognize K_P quants — it may show fewer files than actually exist. Click "View +X variants" or go to Files and versions to see all available downloads.

Specs

4B parameters
42 layers, mixed sliding window (512) + full attention
131K context
Natively multimodal (text, image, video, audio)
18 KV shared layers for memory efficiency
Based on HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive

Recommended Settings

From the official Google Gemma 4 authors:

temperature=1.0, top_p=0.95, min_p=0.05, top_k=64

Important:

Use --jinja flag with llama.cpp for proper chat template handling
Vision/audio support requires the mmproj file alongside the main GGUF

Usage

Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF-compatible runtimes.

Downloads last month: 5,736

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit

View +1 variant