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

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

Are you planning to make gemma-3-27b-it-abliterated compatible with LTX-2 anytime soon?

by aomsan461 - opened Jan 18

Discussion

aomsan461

Jan 18

👇

https://huggingface.co/mlabonne/gemma-3-27b-it-abliterated

DreamFast

Owner Jan 20

👇

https://huggingface.co/mlabonne/gemma-3-27b-it-abliterated

Sure I'll have to try it out first though. My hunch is given that LTX2 was trained on the 12b model, the 27b may have embeddings the DiT doesn't understand and will generate strange results. But hey, one way to find out. Maybe a week or so before I have good internet again to see how it goes.

Parogar

Mar 6

These models can't be used with image node connected, right?

Manderlore

Mar 6

Seems so, the TextGenerateLTX2Prompt node breaks with the error "mat1 and mat2 shapes cannot be multiplied (4096x1152 and 4304x1152)" when you input an image to it and the node works without the image input. But otherwise it works great! (The original text encoder works with an image input for that node.)

DreamFast

Owner Mar 6

Seems so, the TextGenerateLTX2Prompt node breaks with the error "mat1 and mat2 shapes cannot be multiplied (4096x1152 and 4304x1152)" when you input an image to it and the node works without the image input. But otherwise it works great! (The original text encoder works with an image input for that node.)

I'll have to try again to see if anything recent has changed, if I remember correctly I was able to use img2vid and this text encoder. I had that same error using the original video preview node that was provided. However changing that to the Video Combine node it had worked okay.

DreamFast

Owner Mar 7

Ahh the error I was thinking of was [Errno 22] Invalid argument: 'avcodec_send_frame()'; last error log: [aac] Input contains (near) NaN/+-Inf so it's not related.

I had tried again with image2video, using LTX2.0 ComfyUI template. I swapped out some nodes for multi GPU nodes to avoid OOM errors and it seems it's working okay with both the fp8 and fuller version of this text encoder. I also haven't updated my ComfyUI in a couple of weeks. I was using the non distilled version with the fp8 LTX2 model.

Are you trying with the latest LTX 2.3? Just trying to think of things which would break it. There was also another comment with the same error just today too.

shivshankar

Mar 8

this version include vision capablity?

DreamFast

Owner Mar 10

https://huggingface.co/DreamFast/gemma-3-12b-it-heretic-v2 check out version 2 with vision support and nvfp4. I'll leave this thread open for others to read easier.

Tested okay for me here. Let me know how it goes!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment