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

Libraries

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

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

pipe = pipeline("image-text-to-text", model="google/gemma-3-12b-it")
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("google/gemma-3-12b-it")
model = AutoModelForImageTextToText.from_pretrained("google/gemma-3-12b-it")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

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

SGLang

How to use google/gemma-3-12b-it 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 "google/gemma-3-12b-it" \
    --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": "google/gemma-3-12b-it",
		"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 "google/gemma-3-12b-it" \
        --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": "google/gemma-3-12b-it",
		"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 google/gemma-3-12b-it with Docker Model Runner:
```
docker model run hf.co/google/gemma-3-12b-it
```

📋 Documentation Enhancement Suggestion

#33

by CroviaTrust - opened Feb 15

Discussion

CroviaTrust

Feb 15

📋 Documentation Enhancement Suggestion

This observation was generated by Crovia — the AI transparency observation layer.

Crovia does not accuse or judge. It observes publicly available information and suggests improvements.

📊 Quick Stats

Metric	Value
Source	huggingface
Downloads	1386348
Likes	647
Last Updated	2026-02-15

💻 Ready-to-Use Code

from transformers import AutoModel, AutoTokenizer

model_id = "google/gemma-3-12b-it"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModel.from_pretrained(model_id)

# Example usage
inputs = tokenizer("Hello, world!", return_tensors="pt")
outputs = model(**inputs)

📚 Citation

If you use this model, please cite:

@misc {google_gemma_3_12b_it_2026,
  author = {google},
  title = {google/gemma-3-12b-it},
  year = {2026},
  url = {https://huggingface.co/google/gemma-3-12b-it},
  note = {Accessed via CROVIA transparency registry}
}

⚖️ EU AI Act Compliance Checklist

Training data disclosed
License clearly stated
Intended use documented
Model limitations documented
Evaluation metrics provided
Bias/fairness analysis

🔍 Training Data Transparency

Training Data Status: Documentation not found

No training data section was observed in the public model card.

This is an observation, not an accusation. Many valid reasons exist for this status.

If you'd like to improve documentation, consider adding:

Dataset names and versions used
Data collection methodology
Preprocessing steps applied
Known limitations

This may help users understand your model better and prepare for upcoming transparency requirements (e.g., EU AI Act).

Enhancement generated by CROVIA · Package ID: 512e3161c970
Generated at: 2026-02-15T06:00:12.792402Z

This suggestion was generated by Crovia — the AI transparency observation layer.

Crovia does not accuse or judge. It observes publicly available information and suggests documentation improvements.

If this suggestion is helpful, consider adding the recommended sections to your model card.
If not applicable, feel free to close this discussion.

Learn more: croviatrust.com · What is Crovia?

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