Instructions to use llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF",
	filename="Gemma-4-Garnet-31B-it-mmproj-BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-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 llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-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 llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M

Use Docker

docker model run hf.co/llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-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": "llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M

Ollama
How to use llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF with Ollama:
```
ollama run hf.co/llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M
```

Unsloth Studio new

How to use llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF 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 llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF 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 llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF to start chatting

Pi new

How to use llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF: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": "llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-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 llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF with Docker Model Runner:
```
docker model run hf.co/llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M
```

Lemonade

How to use llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF-Q4_K_M

List all available models

lemonade list

🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨

I can no longer upload new models unless I can cover the cost of additional storage.
I host 70+ free models as an independent contributor and this work is unpaid.
Without your support, no more new models can be uploaded.

🎉 Patreon (Monthly) | ☕ Ko-fi (One-time)

Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.

94% fewer refusals (6/100 Uncensored vs 99/100 Original) while preserving model quality (0.0368 KL divergence).

❤️ Support My Work

Creating these models takes significant time, work and compute. If you find them useful consider supporting me:

Platform	Link	What you get
🎉 Patreon	Monthly support	Priority model requests
☕ Ko-fi	One-time tip	My eternal gratitude

Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.

GGUF quantizations of llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic.

This model is great for creative writing and translation, the original base model writing and translations feels very stiff with some odd word choices that might not really fit very well the situation, Gemma-4-Garnet-31B-it-uncensored-heretic aims to fix this issue and improve the writing quality of Gemma 4 31B it.

This is a decensored version of ConicCat/Gemma4-Garnet-31B, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method

Abliteration parameters

Parameter	Value
start_layer_index	26
end_layer_index	46
preserve_good_behavior_weight	0.8239
steer_bad_behavior_weight	0.0001
overcorrect_relative_weight	1.1479
neighbor_count	10

Targeted components

attn.o_proj

Performance

Metric	This model	Original model (Gemma4-Garnet-31B)
KL divergence	0.0368	0 (by definition)
Refusals	✅ 6/100	❌ 99/100

PIQA test results:

Original:

Total questions: 1838
Correct: 1721
Accuracy: 0.9363 (93.63%)
Parse failures: 0

Heretic:

Total questions: 1838
Correct: 1724
Accuracy: 0.9380 (93.80%)
Parse failures: 0

Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections. PIQA (Physical Intuition Question Answering) a ~1,800 questions tests common-sense understanding of how the physical world works with benchmark scores to measure physical reasoning ability.

MMLU test results:

Original:

============================================================

Total questions: 7021
Correct: 6032
Accuracy: 0.8591 (85.91%)
Parse failures: 25

============================================================

Top subjects:

professional_law: 0.7452 (585/785)
moral_scenarios: 0.8167 (361/442)
miscellaneous: 0.9217 (353/383)
professional_psychology: 0.8987 (284/316)
high_school_psychology: 0.9704 (262/270)
high_school_macroeconomics: 0.9188 (181/197)
prehistory: (157/172)
moral_disputes: 0.8218 (143/174)
elementary_mathematics: 0.9185 (169/184)
philosophy: 0.8553 (141/159)

Heretic:

============================================================

Total questions: 7021
Correct: 5954
Accuracy: 0.8480 (84.80%)
Parse failures: 21

============================================================

Top subjects:

professional_law: 0.7223 (567/785)
moral_scenarios: 0.7534 (333/442)
miscellaneous: 0.9243 (354/383)
professional_psychology: 0.8797 (278/316)
high_school_psychology: 0.9667 (261/270)
high_school_macroeconomics: 0.9137 (180/197)
prehistory: 0.9186 (158/172)
moral_disputes: 0.8103 (141/174)
elementary_mathematics: 0.9239 (170/184)
philosophy: 0.8239 (131/159)

MMLU - Massive Multitask Language Understanding, multiple-choice questions across 57 subjects (math, history, law, medicine, etc.).

Quantizations

Filename	Quant	Description
Gemma-4-Garnet-31B-it-uncensored-heretic-BF16.gguf	BF16	Full precision
Gemma-4-Garnet-31B-it-uncensored-heretic-Q8_0.gguf	Q8_0	Near-lossless, recommended
Gemma-4-Garnet-31B-it-uncensored-heretic-Q6_K.gguf	Q6_K	Excellent quality
Gemma-4-Garnet-31B-it-uncensored-heretic-Q5_K_M.gguf	Q5_K_M	Good balance
Gemma-4-Garnet-31B-it-uncensored-heretic-Q5_K_SQwen3.5-27B-ultra-uncensored-heretic-v2-v2-Q5_K_S.gguf	Q5_K_S	Smaller Q5
Gemma-4-Garnet-31B-it-uncensored-heretic-Q4_K_M.gguf	Q4_K_M	Good for limited VRAM
Gemma-4-Garnet-31B-it-uncensored-heretic-Q4_K_S.gguf	Q4_K_S	Smaller Q4
Gemma-4-Garnet-31B-it-uncensored-heretic-Q3_K_L.gguf	Q3_K_L	Low VRAM, decent quality
Gemma-4-Garnet-31B-it-uncensored-heretic-Q3_K_M.gguf	Q3_K_M	Low VRAM, smaller

Vision Projector

Filename	Quant	Description
Gemma-4-Garnet-31B-it-mmproj-BF16.gguf	BF16	Native precision

A Vision Projector File is Required for vision/multimodal capabilities. Use alongside any quantization above.

Usage

Works with llama.cpp, LM Studio, Ollama, and other GGUF-compatible tools.

ConicCat/Gemma4-Garnet-31B

A finetune primarily focused on improving the prose and writing capabilities of Gemma 4. This does generalize strongly to roleplay and most other creative domains as well.

Features:

Improved longform writing capabilites; output context extension allows for prompting for up to 4000 words of text in one go.
Markedly less AI slop and identifiable Gemini-isms in writing.
Improved swipe or output diversity.
Fewer 'soft' refusals in writing.

Datasets

internlm/Condor-SFT-20K for instruct; even though instruct capabilities are not the primary focus, adding some instruct data helps mitigate forgetting and maintains general intellect and instruction following capabilites.
ConicCat/Gutenberg-SFT. A reformatted version of the original Gutenberg DPO dataset by jondurbin for SFT with some slight augmentation to address many of the samples being overly long.
A dataset of backtranslated books. Unfortunately, I am unable to release this set as all of the data is under copyright.
A dash of a certain third owned archive.

Downloads last month: 5,158

GGUF

Model size

31B params

Architecture

gemma4

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Finetuned

ConicCat/Gemma4-Garnet-31B

Finetuned

llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic

Quantized

(3)

this model

llmfan46
/

Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF

🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨

94% fewer refusals (6/100 Uncensored vs 99/100 Original) while preserving model quality (0.0368 KL divergence).

❤️ Support My Work

This is a decensored version of ConicCat/Gemma4-Garnet-31B, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method

Abliteration parameters

Targeted components

Performance

PIQA test results:

MMLU test results:

Quantizations

Vision Projector

Usage

ConicCat/Gemma4-Garnet-31B

Features:

Datasets

Model tree for llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF

Datasets used to train llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF