Instructions to use google/gemma-3n-E2B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-3n-E2B-it with Transformers:

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

pipe = pipeline("image-text-to-text", model="google/gemma-3n-E2B-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-3n-E2B-it")
model = AutoModelForImageTextToText.from_pretrained("google/gemma-3n-E2B-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use google/gemma-3n-E2B-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-3n-E2B-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-3n-E2B-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-3n-E2B-it

SGLang

How to use google/gemma-3n-E2B-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-3n-E2B-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-3n-E2B-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-3n-E2B-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-3n-E2B-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-3n-E2B-it with Docker Model Runner:
```
docker model run hf.co/google/gemma-3n-E2B-it
```

Does this model support multiple audio inputs in a single turn?

#17

by Evan-Lin - opened Aug 18, 2025

Discussion

Evan-Lin

Aug 18, 2025

•

edited Aug 18, 2025

Hello,

Does this model support multiple audio inputs in a single turn?
such as

messages = [
{
    "role": "system",
    "content": [{"type": "text", "text": "You are a helpful assistant."}]
},
{
    "role": "user",
    "content": [
        {"type": "text", "text": "Select the best audio and answer with its number."}
        {"type": "text", "text": "1."}
        {"type": "audio", "audio": "audio1.wav},
        {"type": "text", "text": "2."}
        {"type": "audio", "audio": "audio1.wav},
    ]
}
]

lkv

Google org Sep 3, 2025

Hi @Evan-Lin ,

The model's multimodal capabilities are designed to process audio, but typically it expects a single audio file or stream to be passed into the input. The model's audio encoder takes a single audio stream and converts it into a sequence of tokens that are then interleaved with text tokens for the language model to process.

The standard workflow involves providing one audio file or stream at a time within the user turn. This audio can be a voice recording to be transcribed or a sound to be analyzed.

Kindly refer this link for more information.

We appreciate your exploration and feedback — and we’ll be sure to share updates as more multimodal capabilities become available in future releases.

Thank you.

moghazy0814

Sep 3, 2025

moghazy0814

Sep 3, 2025

moghazy0814

Sep 3, 2025

ريد حريه الحركة و المرح المتستمر مع الابتسامات القويه

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