Instructions to use RedHatAI/gemma-3n-E2B-it-quantized.w4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/gemma-3n-E2B-it-quantized.w4a16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="RedHatAI/gemma-3n-E2B-it-quantized.w4a16")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("RedHatAI/gemma-3n-E2B-it-quantized.w4a16")
model = AutoModelForMultimodalLM.from_pretrained("RedHatAI/gemma-3n-E2B-it-quantized.w4a16", device_map="auto")
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 Settings

vLLM

How to use RedHatAI/gemma-3n-E2B-it-quantized.w4a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/gemma-3n-E2B-it-quantized.w4a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/gemma-3n-E2B-it-quantized.w4a16",
		"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/RedHatAI/gemma-3n-E2B-it-quantized.w4a16

SGLang

How to use RedHatAI/gemma-3n-E2B-it-quantized.w4a16 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 "RedHatAI/gemma-3n-E2B-it-quantized.w4a16" \
    --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": "RedHatAI/gemma-3n-E2B-it-quantized.w4a16",
		"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 "RedHatAI/gemma-3n-E2B-it-quantized.w4a16" \
        --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": "RedHatAI/gemma-3n-E2B-it-quantized.w4a16",
		"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 RedHatAI/gemma-3n-E2B-it-quantized.w4a16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/gemma-3n-E2B-it-quantized.w4a16
```

Error RedHatAI/gemma-3n-E2B-it-quantized.w4a16 is not a multimodal model

by mtobing - opened Oct 18, 2025

Discussion

mtobing

Oct 18, 2025

•

edited Oct 18, 2025

I ran this model using vllm and when I tried to extract text from an image in Open WebUI, I got this error

ERROR 10-18 19:36:15 [serving_chat.py:208]   File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/chat_utils.py", line 553, in mm_processor
ERROR 10-18 19:36:15 [serving_chat.py:208]     return self.mm_registry.create_processor(self.model_config)
ERROR 10-18 19:36:15 [serving_chat.py:208]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 10-18 19:36:15 [serving_chat.py:208]   File "/usr/local/lib/python3.12/dist-packages/vllm/multimodal/registry.py", line 242, in create_processor
ERROR 10-18 19:36:15 [serving_chat.py:208]     raise ValueError(f"{model_config.model} is not a multimodal model")
ERROR 10-18 19:36:15 [serving_chat.py:208] ValueError: RedHatAI/gemma-3n-E2B-it-quantized.w4a16 is not a multimodal model

I saw Input: Audio-Vision-Text for this model.
Is this multimodal? or did i miss something. I ran vllm with this command

python3 -m vllm.entrypoints.openai.api_server
      --model RedHatAI/gemma-3n-E2B-it-quantized.w4a16
      --trust-remote-code
      --limit-mm-per-prompt.image 1
      --limit-mm-per-prompt.video 1
      --limit-mm-per-prompt.audio 1
      --gpu-memory-utilization 0.85
      --max-model-len 4K
      --max-num-seqs 5
      --max-num-batched-tokens 4K
      --host 0.0.0.0
      --port 8000
      --dtype bfloat16

mtobing changed discussion title from Is this multimodal ? to Error RedHatAI/gemma-3n-E2B-it-quantized.w4a16 is not a multimodal model Oct 18, 2025

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