Instructions to use HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced",
	filename="Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_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 Settings

llama.cpp

How to use HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced 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 HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced: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/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced: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/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M

Use Docker

docker model run hf.co/HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M

LM Studio
Jan

vLLM

How to use HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced"
# 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/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced",
		"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/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M

Ollama
How to use HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced with Ollama:
```
ollama run hf.co/HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M
```

Unsloth Studio

How to use HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced 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/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced 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/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced to start chatting

How to use HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced: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/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced: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/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced with Docker Model Runner:
```
docker model run hf.co/HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M
```

Lemonade

How to use HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced:Q4_K_M

Run and chat with the model

lemonade run user.Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M

List all available models

lemonade list

Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced

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

Gemma4-12B (QAT) 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. Built from the official QAT weights, so the 4-bit quant stays close to full-precision quality.

Balanced

The Balanced variant (recommended — 99%+ of users will be happy here) uses optimized full uncensoring tuned especially for agentic coding, reasoning, creative writing and reliability-critical tasks. It reasons before answering and stays dependable and on-instruction. An Aggressive variant, for cases where Balanced still deflects too much, after current testing is not required.

~60% faster with MTP

Ships with an MTP (multi-token-prediction) draft head for speculative decoding — roughly 60% faster generation with identical output (the model verifies every drafted token, so quality is unchanged — pure speed). This release is tuned to pair well with the included MTP head.

llama.cpp:

llama-server \
  -m Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf \
  -md mtp-gemma-4-12B-it.gguf --spec-type draft-mtp \
  -ngl 99 -fa on

Note: the MTP speedup was currently tested by me through llama.cpp (llama-server / llama-cli).

Downloads

File	Type	Size
`Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf`	Q4_K_M (text)	6.9 GB
`mmproj-Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf`	mmproj (vision)	168 MB
`mtp-gemma-4-12B-it.gguf`	MTP speculative drafter	242 MB

Why only Q4_K_M? Gemma 4 is quantization-aware-trained for ~4-bit, so Q4_K_M is the sweet spot — higher-precision quants add size with no real quality gain. Carefully quantized for best quality at 4-bit.

Vision

Load the mmproj alongside the model for image input:

llama-server -m Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf \
  --mmproj mmproj-Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf -ngl 99 -fa on

Recommended sampling

These are dialed in specifically for this HauhauCS build — use them for the intended behaviour and quality:

temperature 0.6
top_k 64
top_p 0.9
min_p 0.05
repeat_penalty 1.1

This release is tuned end-to-end as its own thing; the settings above are part of that and aren't the stock Gemma defaults.

Specs

12B dense · 256K (262144) context
Vision (image input) via mmproj
Based on Gemma 4 12B by Google DeepMind

Compatibility

Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF runtimes.
Multi-GPU + LM Studio: I've personally noticed Gemma 4 can crash under LM Studio's tensor-split mode — use a single GPU (layer-split or priority order) for this model.

Acknowledgements

Google DeepMind — Gemma 4.
The included mtp-gemma-4-12B-it.gguf speculative draft head comes from Unsloth's Gemma 4 release — many thanks to the Unsloth team for it.

* Tested with both automated and manual refusal benchmarks — none have been found in standard use. A small number of edge-case prompts deflect on the first ask but comply on a re-ask or strategic framing. If you hit one that's actually obstructive to your use case, join the Discord and flag it so I can work on it in a future revision.

Downloads last month: 59,538

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

4-bit

View +1 variant

Model tree for HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Quantized

(214)

this model