Instructions to use nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16")
model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16

SGLang

How to use nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 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 "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16
```

NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 / model-00009-of-00225.safetensors

dmax123

Add files using upload-large-folder tool

b420a5c verified 4 days ago

download

history blame contribute delete

4.99 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: e79f76ba9ab50840137ab0ac6c141d36d50e0b63e310fcbf193f61c6436aa6b2
Size of remote file:: 4.99 GB
SHA256:: a87c11c65a4175655edddbd15f9ec86b731d32ee305855aceeb2a35e134e313b

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.