Instructions to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 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-Super-120B-A12B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4

SGLang

How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 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-Super-120B-A12B-NVFP4" \
    --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": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",
		"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 "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4" \
        --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": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4
```

Spark not using NVFP4?

#18

by D-Lynch - opened Mar 25

Discussion

D-Lynch

Mar 25

•

edited Mar 25 by

NV-DLynch

Using the provided docker and instructions in the README for DGX Spark:
docker pull vllm/vllm-openai:v0.17.1-cu130

Then

docker run --gpus all \
  --ipc=host \
  --entrypoint vllm \
  -v ~/models:/workspace/models \
  -p 8000:8000 \
  -e VLLM_NVFP4_GEMM_BACKEND=marlin \
  -e VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 \
  -e VLLM_FLASHINFER_ALLREDUCE_BACKEND=trtllm \
  vllm/vllm-openai:v0.17.1-cu130 \
  serve /workspace/models/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 \
  --served-model-name nemotron-3-super \
  --host 0.0.0.0 \
  --port 8000 \
  --async-scheduling \
  --dtype auto \
  --kv-cache-dtype fp8 \
  --tensor-parallel-size 1 \
  --pipeline-parallel-size 1 \
  --data-parallel-size 1 \
  --trust-remote-code \
  --gpu-memory-utilization 0.90 \
  --enable-chunked-prefill \
  --max-num-seqs 4 \
  --max-model-len 394000 \
  --attention-backend TRITON_ATTN \
  --mamba_ssm_cache_dtype float32 \
  --moe-backend marlin

This message is in the log:

(EngineCore_DP0 pid=99) WARNING 03-25 18:13:38 [marlin_utils_fp4.py:150] Your GPU does not have native support for FP4 computation but FP4 quantization is being used. Weight-only FP4 compression will be used leveraging the Marlin kernel. This may degrade performance for compute-heavy workloads.

NV-DLynch

NVIDIA org Mar 25

https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4/discussions/14#69bef5db49285df878c491b8

That comment gives instructions to use a different repo that uses VLLM_CUTLASS to enable NVFP4

https://github.com/eugr/spark-vllm-docker/commit/9e089acf2bf1c8e78dc1e59fd9be03c3079ea2f8

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