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
```

cache_size_limit reached

#26

by uesenpai - opened Jun 18, 2025

Discussion

uesenpai

Jun 18, 2025

I think that error it is something to do with KV.

Is there any method exist to empty KV cache manually?

BalakrishnaCh

Google org Jun 18, 2025

Hi @uesenpai ,

Welcome to Google Gemma family of open source models, The KV cache can occupy a significant portion of memory and become a bottleneck for long-context generation. Memory efficient caches focus on trading off speed for reduced memory usage. This is especially important for large language models (LLMs) and if your hardware is memory constrained.
The OffloadedCache saves GPU memory by moving the KV cache for most model layers to the CPU. Only the current layer cache is maintained on the GPU during a models forward iteration over the layers. OffloadedCache asynchronously prefetches the next layer cache and sends the previous layer cache back to the CPU.

This cache strategy always generates the same result as DynamicCache and works as a drop-in replacement or fallback. You may want to use OffloadedCache if you have a GPU and you’re getting out-of-memory (OOM) errors.

The above mentioned mechanism can be utilized by passing the parameter cache_implementation="offloaded_static" while calling the generate() method or else you can pass use_cache=False to disable the cache.

Please find the attached screenshot for your reference.

If you required any further assistance please feel free to reach out to me.

Thanks.

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