Instructions to use RedHatAI/gemma-4-31B-it-FP8-block with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/gemma-4-31B-it-FP8-block with Transformers:

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

pipe = pipeline("image-text-to-text", model="RedHatAI/gemma-4-31B-it-FP8-block")
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("RedHatAI/gemma-4-31B-it-FP8-block")
model = AutoModelForImageTextToText.from_pretrained("RedHatAI/gemma-4-31B-it-FP8-block")
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 RedHatAI/gemma-4-31B-it-FP8-block with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/gemma-4-31B-it-FP8-block"
# 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-4-31B-it-FP8-block",
		"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-4-31B-it-FP8-block

SGLang

How to use RedHatAI/gemma-4-31B-it-FP8-block 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-4-31B-it-FP8-block" \
    --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-4-31B-it-FP8-block",
		"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-4-31B-it-FP8-block" \
        --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-4-31B-it-FP8-block",
		"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-4-31B-it-FP8-block with Docker Model Runner:
```
docker model run hf.co/RedHatAI/gemma-4-31B-it-FP8-block
```

Could you also provide FP8-block version of the gemma-4-31B-it drafted model?

by RayHuang1991 - opened 17 days ago

Discussion

RayHuang1991

17 days ago

this quant version can not use https://huggingface.co/google/gemma-4-31B-it-assistant

bdellabe

Red Hat AI org 13 days ago

Hi @RayHuang1991 , it looks like this follows similar naming structure to the original model. If you'd like to try it out yourself, you can mimic the creation script. No specialized hardware required

RayHuang1991

12 days ago

Hi @RayHuang1991 , it looks like this follows similar naming structure to the original model. If you'd like to try it out yourself, you can mimic the creation script. No specialized hardware required

Thank you! With the new release of vllm, I can use the Gemma 4 31B assistant as MTP now. But there are issues with the combination (RedHatAI/gemma-4-31B-it-FP8-block + Gemma-4-31B-it-assistant), even if the rejection rate of speculative decoding is low, the output is very different for same task as compared to the gemma-4-31B-it-FP8-block alone.
the MTP drafted model shares some layers with the main model, I think this might cause discrepancies when Main model is slightly different from drafted model

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