Instructions to use vrfai/gemma-4-31B-it-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vrfai/gemma-4-31B-it-fp8 with Transformers:

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

pipe = pipeline("text-generation", model="vrfai/gemma-4-31B-it-fp8")
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("vrfai/gemma-4-31B-it-fp8")
model = AutoModelForImageTextToText.from_pretrained("vrfai/gemma-4-31B-it-fp8")
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 vrfai/gemma-4-31B-it-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vrfai/gemma-4-31B-it-fp8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vrfai/gemma-4-31B-it-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vrfai/gemma-4-31B-it-fp8

SGLang

How to use vrfai/gemma-4-31B-it-fp8 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 "vrfai/gemma-4-31B-it-fp8" \
    --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": "vrfai/gemma-4-31B-it-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "vrfai/gemma-4-31B-it-fp8" \
        --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": "vrfai/gemma-4-31B-it-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vrfai/gemma-4-31B-it-fp8 with Docker Model Runner:
```
docker model run hf.co/vrfai/gemma-4-31B-it-fp8
```

gemma-4-31B-it-fp8

FP8 quantized version of google/gemma-4-31B-it (31B params, server model). Produced and maintained by vrfai.

Quantization Details

This model was quantized using NVIDIA ModelOpt with the following configurations:

Property	Value
Base model	google/gemma-4-31B-it
Quant method	NVIDIA ModelOpt (FP8 E4M3 - `num_bits: (4, 3)`)
Weight scheme	Per-channel (`axis: 0`)
Input activation	Dynamic Per-token (`type: dynamic`)
Calibration algorithm	max

Usage

You can deploy this model using vLLM with the modelopt quantization backend. Please ensure you refer to the vLLM documentation for Gemma 4 for advanced serving options.

vllm serve vrfai/gemma-4-31B-it-fp8
  --quantization modelopt \
  --max-model-len 32768 \
  --max-num-seqs 128 \
  --max-num-batched-tokens 8192 \
  --gpu-memory-utilization 0.95 \
  --kv-cache-dtype fp8 \
  --enable-prefix-caching \
  --enable-auto-tool-choice \
  --reasoning-parser gemma4 \
  --tool-call-parser gemma4 \
  --async-scheduling \
  --trust-remote-code

Downloads last month: 355

Safetensors

Model size

31B params

Tensor type

F32

BF16

F8_E4M3

Collection including vrfai/gemma-4-31B-it-fp8

gemma-4-Optimized

Collection

2 items • Updated 28 days ago • 1