Instructions to use mlabonne/gemma-3-12b-it-abliterated-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlabonne/gemma-3-12b-it-abliterated-v2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="mlabonne/gemma-3-12b-it-abliterated-v2")
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 AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("mlabonne/gemma-3-12b-it-abliterated-v2")
model = AutoModelForMultimodalLM.from_pretrained("mlabonne/gemma-3-12b-it-abliterated-v2")
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 = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mlabonne/gemma-3-12b-it-abliterated-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlabonne/gemma-3-12b-it-abliterated-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlabonne/gemma-3-12b-it-abliterated-v2",
		"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/mlabonne/gemma-3-12b-it-abliterated-v2

SGLang

How to use mlabonne/gemma-3-12b-it-abliterated-v2 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 "mlabonne/gemma-3-12b-it-abliterated-v2" \
    --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": "mlabonne/gemma-3-12b-it-abliterated-v2",
		"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 "mlabonne/gemma-3-12b-it-abliterated-v2" \
        --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": "mlabonne/gemma-3-12b-it-abliterated-v2",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use mlabonne/gemma-3-12b-it-abliterated-v2 with Docker Model Runner:
```
docker model run hf.co/mlabonne/gemma-3-12b-it-abliterated-v2
```

Just like v1, on Ollama, generation totaly broken

by MichaelBTryin - opened Dec 14, 2025

Discussion

MichaelBTryin

Dec 14, 2025

ollama run hf.co/mlabonne/gemma-3-4b-it-abliterated-v2-GGUF:Q4_K_M

Hello
Hello! How can I help you?
How can I help you today?

What is a chicken
How can I help you today?
How can I help you today?
How can I help you today? How can I help you help you today.
How can you? How can I help you today

How can help you help you help you today
How can help you
How can help you help you?
How can help you
How can help you can help you?
How can you
How can you do you?
How can you do you
How can do
How can you do?
How can you do you do you do you do you?
How can you do
How can you
How can you
How can you do
How can you

How can you do
How can you
How can you do

How can you
How can you?
How can you do you?
How can you

How can you do you
How can you
How can you do

How can you do you

How can you
How can you do you
How can you
How can
How can you
How can you
How can you do you can you do you
How can

How can you
How can you
How can you can you

How can you

How can you
How can you do you
How can you

How can
.... You get the picture.

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