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
```

Chris-Alexiuk

avskliar-nvidia commited on May 1

Commit

4f0cf9d

1 Parent(s): 3efc779

Fix: rescue whitespace-only final_content (e.g. "\n"), not just None (#29)

Browse files

- Fix: rescue whitespace-only final_content (e.g. "\n"), not just None (0ae40c7de53db9c6e22a2062c99aa45c527d2ff5)

Co-authored-by: Andrii Skliar <avskliar-nvidia@users.noreply.huggingface.co>

Files changed (1) hide show

super_v3_reasoning_parser.py +1 -1

super_v3_reasoning_parser.py CHANGED Viewed

@@ -15,7 +15,7 @@ class SuperV3ReasoningParser(DeepSeekR1ReasoningParser):
                 request.chat_template_kwargs.get("enable_thinking") is False
                 or request.chat_template_kwargs.get("force_nonempty_content") is True
             )
-            and final_content is None
         ):
             """
             The original `deepseek_r1` reasoning parser this inherits from will automatically put everything in the reasoning content when it cannot parse out reasoning. This was fine for the DeepSeek R1 model that was not intended to be used without reasoning.

                 request.chat_template_kwargs.get("enable_thinking") is False
                 or request.chat_template_kwargs.get("force_nonempty_content") is True
             )
+            and (final_content is None or not final_content.strip())
         ):
             """
             The original `deepseek_r1` reasoning parser this inherits from will automatically put everything in the reasoning content when it cannot parse out reasoning. This was fine for the DeepSeek R1 model that was not intended to be used without reasoning.