Instructions to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-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 EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

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 EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

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 EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

Use Docker

docker model run hf.co/EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

LM Studio
Jan

vLLM

How to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-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": "EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-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/EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

SGLang

How to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF with Ollama:
```
ollama run hf.co/EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL
```

Unsloth Studio

How to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-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 EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-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 EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF to start chatting

How to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

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": "EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

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 "EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL" \
  --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 EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF with Docker Model Runner:
```
docker model run hf.co/EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL
```

Lemonade

How to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

Run and chat with the model

lemonade run user.gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-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 EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

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 EZForever/gemma-4-12B-it-qat-uncensored-heretic-UDmerge-GGUF:Q4_K_XL

Run Hermes

hermes

Atomic Chat

UPDATE 2026-07-20: Download & use Google's new chat template from here for better speed and accurancy. See Unsloth's post for details.

WARNING: Created with heavy LLM assistance (Zoo Code + DeepSeek-V4-Flash). Use at your own discretion.

Cosplayed Frankenstein and grafted/"merged" llmfan46's abliterated tensors onto Unsloth's lossless Q4_0 quant. Should yield better accurancy and refusal rate than a naive abliterated Q4_0 quant.

This repo contains two variants: "UDmerge-Q4_K_XL" have the abliterated tensors (blk.N.attn_output.weight, where N is 24 to 34 inclusive) quantized to Q4_0, while "UDmerge-Q4_K_XXL" quantizes them to Q8_0. The latter improves refusal rate by a lot, while basically not affecting TG speed (your mileage may vary).

Use Unsloth's mmproj and mtp GGUF files for multimodal and MTP support.

-	QAT BF16	QAT Q4_0	QAT Q4_K_M	QAT UDmerge-Q4_K_XL	QAT UDmerge-Q4_K_XXL	-	PTQ BF16	PTQ Q4_0*	PTQ Q4_K_M
Size (GB)	23.9	7.60	7.38	6.72	6.81	-	23.9	7.00	8.54
PPL	3.423	3.716	3.734	3.343	3.400	-	3.941	4.733	4.950
KLD	0.0000	0.1752	0.2463	0.1012	0.0903	-	0.0000	0.3794	0.3430
Refusal	10%	10%	22%	24%	14%	-	11%	10%	9%
MMLU-val	74.59%	74.00%	74.40%	75.77%	74.66%	-	71.00%	65.77%	71.20%
MMLU-val %flips	0.00%	3.33%	4.11%	3.14%	0.98%	-	0.00%	10.71%	4.38%
MMLU-val %allflips	0.00%	4.18%	5.29%	3.66%	1.37%	-	0.00%	13.85%	5.62%

Legend:

*: Quant made with importance matrix ("imatrix"), results may be unreliable

PPL and KLD are tested on the same dataset as Heretic, i.e. the first 100 questions in the mlabonne/harmless_alpaca dataset's test split. Note that the dataset is processed differently, thus the numbers here are only meaningful for comparsions in this table, not with other models.

Refusal rates are also tested on the same dataset as Heretic, i.e. the first 100 questions in the mlabonne/harmful_behaviors dataset's test split. The test script, however, is adapted from Heretic to support testing needs. Note that the original author claimed 11% refusal rate for 31B and 26B-A4B models, and 6%~7% for 12B, which is not reproduced here; this is probably due to test method differences, but please take the numbers here with a grain of salt.

"MMLU-val" refers to zero-shot testing on the cais/mmlu dataset's validation split (1531 questions). All tests are done once with temperature 0.0 and reasoning off. MTP is not enabled during testing. See the test script and raw data for details.

"%flips" and "%allflips" refer to the percentage of changed answers compared to BF16 models, measured as by the paper Accuracy is Not All You Need (arXiv:2407.09141). "%flips" is the percentage of "right-to-wrong" and "wrong-to-right" changes, while "%allflips" is the percentage of all changed answers.

More test results

-	QAT BF16	QAT Q4_0	QAT Q4_K_M	QAT UDmerge-Q4_K_XL	QAT UDmerge-Q4_K_XXL	-	PTQ BF16	PTQ Q4_0*	PTQ Q4_K_M
MMLU-val-v1	75.57%	75.38%	75.51%	76.81%	75.44%	-	73.81%	70.48%	73.22%
MMLU-val-v1 %nulls	0.78%	0.78%	3.46%	1.76%	0.78%	-	0.20%	0.20%	0.07%
MMLU-val-v1 %flips	0.00%	2.55%	5.68%	3.85%	0.65%	-	0.00%	8.69%	4.77%
MMLU-val-v1 %allflips	0.00%	3.46%	8.23%	5.36%	0.78%	-	0.00%	12.21%	6.92%

"MMLU-val-v1" numbers are "MMLU-val" test done by an older version of the test script, which does not enforce grammar constraints on answer format. These number are less representative than the ones given above (?), and are kept here for reference purposes only. "%nulls" here refers to the percentage of "null answers", i.e. answers that are not in the required format, thus not parsable.

More information, including test scripts and raw test data, will be released soon.