Instructions to use google/gemma-3n-E4B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-3n-E4B-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-E4B-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-E4B-it")
model = AutoModelForImageTextToText.from_pretrained("google/gemma-3n-E4B-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
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use google/gemma-3n-E4B-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-E4B-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-E4B-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-E4B-it

SGLang

How to use google/gemma-3n-E4B-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-E4B-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-E4B-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-E4B-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-E4B-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-E4B-it with Docker Model Runner:
```
docker model run hf.co/google/gemma-3n-E4B-it
```

VRAM usage with transformers

#29

by JPSun56 - opened Jul 15, 2025

Discussion

JPSun56

Jul 15, 2025

I conducted tests on Gemma 3n models using Transformers on an RTX 4090 GPU. The observed VRAM usage was as follows:

E2B: 11.733 GB

E4B: 16.229 GB

These results clearly exceed typical portable device levels. Additionally, the VRAM usage shows minimal variation between different modalities. This leads to questions regarding the dynamic loading mechanism: is dynamic loading unsupported by Transformers, or does it only activate when VRAM resources become limited?

lcvrjqnr

Jul 16, 2025

same in jetson agx orin.

JPSun56

Jul 16, 2025

The answer from Chat-GPT(o3) :
A: When Transformers ≥4.53 is used with Accelerate, PLE caching and visual/audio weight diversion will be automatically enabled. The judgment condition is "Is OOM possible":

If the GPU memory is sufficient (like RTX4090), Accelerate determines that it is safe and all weights are still put into the GPU at once, so you see 11–16GB.

Just use device_map="auto" with max_memory={'cuda:0':'3GiB'} or add 4‑bit quantization to force PLE etc. to move back to the CPU - at this time, the VRAM of E2B/E4B will drop to the official ~~2GB /~~3GB.
To further reduce it, use Mix‑n‑Match to cut smaller sub-models or exclude visual/audio weights.

BalakrishnaCh

Google org Oct 16, 2025

Hi,

Apologies for the late reply, could you please confirm whether the above query is resolved or do you required any further assistance please let us know.

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