Instructions to use LilaRest/gemma-4-31B-it-NVFP4-turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LilaRest/gemma-4-31B-it-NVFP4-turbo with Transformers:

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

pipe = pipeline("text-generation", model="LilaRest/gemma-4-31B-it-NVFP4-turbo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("LilaRest/gemma-4-31B-it-NVFP4-turbo")
model = AutoModelForCausalLM.from_pretrained("LilaRest/gemma-4-31B-it-NVFP4-turbo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
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 LilaRest/gemma-4-31B-it-NVFP4-turbo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LilaRest/gemma-4-31B-it-NVFP4-turbo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LilaRest/gemma-4-31B-it-NVFP4-turbo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LilaRest/gemma-4-31B-it-NVFP4-turbo

SGLang

How to use LilaRest/gemma-4-31B-it-NVFP4-turbo 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 "LilaRest/gemma-4-31B-it-NVFP4-turbo" \
    --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": "LilaRest/gemma-4-31B-it-NVFP4-turbo",
		"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 "LilaRest/gemma-4-31B-it-NVFP4-turbo" \
        --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": "LilaRest/gemma-4-31B-it-NVFP4-turbo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LilaRest/gemma-4-31B-it-NVFP4-turbo with Docker Model Runner:
```
docker model run hf.co/LilaRest/gemma-4-31B-it-NVFP4-turbo
```

Just squeeze 4-5 GB more.

by emircanerkul - opened Apr 10

Discussion

emircanerkul

Apr 10

Why not squeeze a bit more to fit 16gb vram gpus? I tested gemma-4-26B-A4B i4-lowest one with 6800xt and got 70tps. I wonder if this full model good or moe one

LilaRest

Owner Apr 10

This quant targets Blackwell FP4 tensor cores (RTX 5090, PRO 6000, etc.), so it wouldn't benefit AMD GPUs anyway. I've already quantized the most lossless layers. Pushing further might get it closer to 16GB, but you wouldn't have enough space left for the KV cache.

emircanerkul

Apr 10

I see, thank you.

emircanerkul changed discussion status to closed Apr 10

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