Instructions to use DreamFast/gemma-3-12b-it-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DreamFast/gemma-3-12b-it-heretic with Transformers:

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

pipe = pipeline("text-generation", model="DreamFast/gemma-3-12b-it-heretic")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("DreamFast/gemma-3-12b-it-heretic")
model = AutoModelForImageTextToText.from_pretrained("DreamFast/gemma-3-12b-it-heretic")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use DreamFast/gemma-3-12b-it-heretic with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DreamFast/gemma-3-12b-it-heretic",
	filename="gguf/gemma-3-12b-it-heretic-Q3_K_M.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use DreamFast/gemma-3-12b-it-heretic with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DreamFast/gemma-3-12b-it-heretic:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DreamFast/gemma-3-12b-it-heretic:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DreamFast/gemma-3-12b-it-heretic:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DreamFast/gemma-3-12b-it-heretic: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 DreamFast/gemma-3-12b-it-heretic:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DreamFast/gemma-3-12b-it-heretic: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 DreamFast/gemma-3-12b-it-heretic:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DreamFast/gemma-3-12b-it-heretic:Q4_K_M

Use Docker

docker model run hf.co/DreamFast/gemma-3-12b-it-heretic:Q4_K_M

LM Studio
Jan

vLLM

How to use DreamFast/gemma-3-12b-it-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DreamFast/gemma-3-12b-it-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DreamFast/gemma-3-12b-it-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DreamFast/gemma-3-12b-it-heretic:Q4_K_M

SGLang

How to use DreamFast/gemma-3-12b-it-heretic 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 "DreamFast/gemma-3-12b-it-heretic" \
    --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": "DreamFast/gemma-3-12b-it-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "DreamFast/gemma-3-12b-it-heretic" \
        --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": "DreamFast/gemma-3-12b-it-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use DreamFast/gemma-3-12b-it-heretic with Ollama:
```
ollama run hf.co/DreamFast/gemma-3-12b-it-heretic:Q4_K_M
```

Unsloth Studio new

How to use DreamFast/gemma-3-12b-it-heretic 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 DreamFast/gemma-3-12b-it-heretic 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 DreamFast/gemma-3-12b-it-heretic to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DreamFast/gemma-3-12b-it-heretic to start chatting

Docker Model Runner
How to use DreamFast/gemma-3-12b-it-heretic with Docker Model Runner:
```
docker model run hf.co/DreamFast/gemma-3-12b-it-heretic:Q4_K_M
```

Lemonade

How to use DreamFast/gemma-3-12b-it-heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DreamFast/gemma-3-12b-it-heretic:Q4_K_M

Run and chat with the model

lemonade run user.gemma-3-12b-it-heretic-Q4_K_M

List all available models

lemonade list

Gemma 3 12B IT - Heretic (Abliterated)

An abliterated version of Google's Gemma 3 12B IT created using Heretic. This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for video generation models like LTX-2.

Version 2 is now available

Check out Gemma 3 12b it Heretic v2 which has vision capabilities, NVFP4 support and decensored with Heretic v1.2.0. It'd be better to use v2.

This current v1 has no vision support and wont work with nodes like TextGenerateLTX2Prompt.

Model Details

Base Model: google/gemma-3-12b-it
Abliteration Method: Heretic v1.1.0
Trial Selected: Trial 99
Refusals: 7/100 (vs 100/100 original)
KL Divergence: 0.0826 (minimal model damage)

Files

HuggingFace Format (for transformers, llama.cpp conversion)

model-00001-of-00005.safetensors
model-00002-of-00005.safetensors
...
config.json
tokenizer.model
tokenizer_config.json

ComfyUI Format (for LTX-2 text encoder)

comfyui/gemma_3_12B_it_heretic.safetensors          # bf16, 22GB
comfyui/gemma_3_12B_it_heretic_fp8_e4m3fn.safetensors  # fp8, 11GB

GGUF Format (for llama.cpp)

Quant	Size	Quality	Recommendation
F16	22GB	Lossless	Reference, same as original
Q8_0	12GB	Excellent	Best quality quantization
Q6_K	9.0GB	Very Good	High quality, good compression
Q5_K_M	7.9GB	Good	Balanced quality/size
Q5_K_S	7.7GB	Good	Slightly smaller Q5
Q4_K_M	6.8GB	Good	⭐ Recommended
Q4_K_S	6.5GB	Decent	Smaller Q4 variant
Q3_K_M	5.6GB	Acceptable	For very low VRAM only

gguf/gemma-3-12b-it-heretic-f16.gguf
gguf/gemma-3-12b-it-heretic-Q8_0.gguf
gguf/gemma-3-12b-it-heretic-Q6_K.gguf
gguf/gemma-3-12b-it-heretic-Q5_K_M.gguf
gguf/gemma-3-12b-it-heretic-Q5_K_S.gguf
gguf/gemma-3-12b-it-heretic-Q4_K_M.gguf
gguf/gemma-3-12b-it-heretic-Q4_K_S.gguf
gguf/gemma-3-12b-it-heretic-Q3_K_M.gguf

Note: GGUF support in ComfyUI for Gemma text encoders is experimental. See PR #402 for status. The GGUFs work with llama.cpp directly.

Do abliterated models makes a difference for LTX2?

I had a deep dive into this topic and found that, maybe not. While it does vary slightly the output of the video, most of the abliteration is on layer 48, the final decision making layer. LTXV averages all the layers which may wash out layer 48s difference. Still it'd be more interesting for someone with more knowledge to confirm this.

Usage

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "DreamFast/gemma-3-12b-it-heretic",
    device_map="auto",
    torch_dtype=torch.bfloat16
)
tokenizer = AutoTokenizer.from_pretrained("DreamFast/gemma-3-12b-it-heretic")

prompt = "Write a story about a bank heist"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

With ComfyUI (LTX-2)

Download the ComfyUI format file:
- comfyui/gemma_3_12B_it_heretic.safetensors (bf16, 22GB) or
- comfyui/gemma_3_12B_it_heretic_fp8_e4m3fn.safetensors (fp8, 11GB)
Place in ComfyUI/models/text_encoders/
In your LTX-2 workflow, use the LTXAVTextEncoderLoader node and select the heretic file

Tip: For multi-GPU setups or CPU offloading, check out ComfyUI-LTX2-MultiGPU for optimized LTX-2 workflows.

With llama.cpp

# Using llama-server
llama-server -m gemma-3-12b-it-heretic-Q4_K_M.gguf

# Or with llama-cli
llama-cli -m gemma-3-12b-it-heretic-Q4_K_M.gguf -p "Write a story about a bank heist"

Why Abliterate?

Even when Gemma doesn't outright refuse a prompt, it may "sanitize" or weaken certain concepts in the embeddings. For video generation with LTX-2, this can result in:

Weaker adherence to creative prompts
Softened or altered visual outputs
Less faithful representation of requested content

Abliteration removes this soft censorship, resulting in more faithful prompt encoding.

Abliteration Process

Created using Heretic with the following evaluation results:

* Evaluating...
  * Obtaining first-token probability distributions...
  * KL divergence: 0.0826
  * Counting model refusals...
  * Refusals: 7/100

The low KL divergence (0.0826) indicates minimal model damage, while 7/100 refusals means 93% of previously-refused prompts now work.

Limitations

This model inherits all limitations of the base Gemma 3 12B model
Abliteration reduces but does not completely eliminate refusals
NVFP4 quantization is not supported for text encoders in ComfyUI (use fp8 instead)