Instructions to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive",
	filename="Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive: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 HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive: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 HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Use Docker

docker model run hf.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

LM Studio
Jan

vLLM

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive",
		"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/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Ollama
How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with Ollama:
```
ollama run hf.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M
```

Unsloth Studio new

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive 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 HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive 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 HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive to start chatting

Pi new

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive: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 HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Run Hermes

hermes

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

Lemonade

How to use HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M

List all available models

lemonade list

HauhauCS commited on Apr 2

Commit

b54dcf3

verified ·

1 Parent(s): b36bdfb

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +94 -0

README.md ADDED Viewed

	@@ -0,0 +1,94 @@

+---
+license: gemma
+tags:
+  - uncensored
+  - gemma4
+  - gguf
+  - vision
+  - multimodal
+  - audio
+language:
+  - en
+  - multilingual
+pipeline_tag: image-text-to-text
+base_model: google/gemma-4-4b-it
+---
+# Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
+Gemma 4 4B uncensored by HauhauCS. **0/465 Refusals\***
+## About
+No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.
+These are meant to be the best lossless uncensored models out there.
+## Aggressive Variant
+Stronger uncensoring — model is fully unlocked and won't refuse prompts. May occasionally append short disclaimers (baked into base model training, not refusals) but full content is always generated.
+For a more conservative uncensor that keeps some safety guardrails, check the Balanced variant when it's available.
+## Downloads
+| File | Quant | Size |
+|------|-------|------|
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf) | Q8_K_P | 7.6 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf) | Q6_K_P | 5.9 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf) | Q5_K_P | 5.5 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf) | Q5_K_M | 5.4 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf) | Q4_K_P | 5.1 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf) | Q4_K_M | 5.0 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf) | IQ4_XS | 4.8 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf) | Q3_K_P | 4.6 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf) | Q3_K_M | 4.6 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf) | IQ3_M | 4.4 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf) | Q2_K_P | 4.2 GB |
+| [mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf) | mmproj (f16) | 945 MB |
+All quants generated with importance matrix (imatrix) for optimal quality preservation on abliterated weights.
+## What are K_P quants?
+K_P ("Perfect") quants are HauhauCS custom quantizations that use model-specific analysis to selectively preserve quality where it matters most. Each model gets its own optimized quantization profile.
+A K_P quant effectively bumps quality up by 1-2 quant levels at only ~5-15% larger file size than the base quant. Fully compatible with llama.cpp, LM Studio, and any GGUF-compatible runtime — no special builds needed.
+## 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 [google/gemma-4-4b-it](https://huggingface.co/google/gemma-4-4b-it)
+## Recommended Settings
+From the official Google Gemma 4 authors:
+- `temperature=1.0, top_p=0.95, 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.
+```bash
+# Text only
+llama-cli -m Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
+  --jinja -c 8192 -ngl 99
+# With vision/audio
+llama-cli -m Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
+  --mmproj mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf \
+  --jinja -c 8192 -ngl 99
+```
+**Note:** K_P quants may show as "?" in LM Studio's quant column. This is a display issue only — the model loads and runs fine. LM Studio doesn't recognize the K_P naming convention yet.
+**Note:** IQ2_M is not available for this model due to a llama.cpp limitation with KV shared layers and importance matrix generation.