Instructions to use HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP",
	filename="Gemma4-31B-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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP 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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP: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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP: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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP: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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M

Use Docker

docker model run hf.co/HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M

LM Studio
Jan

vLLM

How to use HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP"
# 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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP",
		"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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M

Ollama
How to use HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP with Ollama:
```
ollama run hf.co/HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M
```

Unsloth Studio

How to use HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP 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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP 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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP to start chatting

How to use HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP: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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP 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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP: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/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP: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 "HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP: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"

Docker Model Runner
How to use HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP with Docker Model Runner:
```
docker model run hf.co/HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M
```

Lemonade

How to use HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP:Q4_K_M

Run and chat with the model

lemonade run user.Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP-Q4_K_M

List all available models

lemonade list

HauhauCS commited on 12 days ago

Commit

9654466

0 Parent(s):

initial commit

Browse files

Files changed (5) hide show

.gitattributes +38 -0
Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf +3 -0
README.md +96 -0
mmproj-Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf +3 -0
mtp-gemma-4-31B-it.gguf +3 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1,38 @@

+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+mtp-gemma-4-31B-it.gguf filter=lfs diff=lfs merge=lfs -text

Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:71667f9e601a4b914a98425c59150b731f6e15d260d661dbd1f1ee07469fc7db
+size 18687062176

README.md ADDED Viewed

	@@ -0,0 +1,96 @@

+---
+license: gemma
+tags:
+  - uncensored
+  - gemma4
+  - gguf
+  - vision
+  - multimodal
+  - agentic
+  - coding
+  - creative-writing
+  - roleplay
+  - rp
+  - conversational
+language:
+  - en
+pipeline_tag: image-text-to-text
+base_model: google/gemma-4-31B-it
+---
+# Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP
+> **[Join the Discord](https://discord.gg/SZ5vacTXYf)** for updates, roadmaps, projects, or just to chat.
+Gemma4-31B (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.
+## ~53% faster with MTP
+Ships with an MTP (multi-token-prediction) draft head for **speculative decoding** — roughly **53% 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:
+```bash
+llama-server \
+  -m Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf \
+  -md mtp-gemma-4-31B-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 |
+|------|------|------|
+| `Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf` | Q4_K_M (text) | 18.7 GB |
+| `mmproj-Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf` | mmproj (vision) | 1.2 GB |
+| `mtp-gemma-4-31B-it.gguf` | MTP speculative drafter | 280 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:
+```bash
+llama-server -m Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf \
+  --mmproj mmproj-Gemma4-31B-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
+- 31B dense · 256K (262144) context
+- Vision (image input) via mmproj
+- Based on [Gemma 4 31B](https://huggingface.co/google/gemma-4-31B-it) 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-4-31B-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](https://discord.gg/SZ5vacTXYf) and flag it so I can work on it in a future revision._

mmproj-Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7bef0d0fb3e85fc2941ec5f1c375febf3742645f158132a43ced557093aea841
+size 1200726016

mtp-gemma-4-31B-it.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c4e583fc5982439080114bbc1b7edaec361f9d4c9193d6bed606a3de401b62
+size 279954368