Instructions to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 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-BF16 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-BF16", 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-BF16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-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-Super-120B-A12B-BF16"
# 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-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16

SGLang

How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-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-Super-120B-A12B-BF16" \
    --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-BF16",
		"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-BF16" \
        --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-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
```

Rescue whitespace-only content + add streaming reasoning promotion

#26

by avskliar-nvidia - opened May 15

base: refs/heads/main

←

from: refs/pr/26

Discussion Files changed

+53

-2

avskliar-nvidia

NVIDIA org May 15

Brings this parser in line with the version that ships with the NVFP4 sibling (discussions #29 and #30 on nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4).

Rescue whitespace-only final_content. When the model stops at the </think>\n boundary, the base DeepSeek R1 parser returns final_content="\n" (not None). The current rescue check only fires on final_content is None, so whitespace slips through and enable_thinking=False / force_nonempty_content=True users see a blank reply with the answer trapped in reasoning_content. The fix extends the check to whitespace-only strings.
Streaming reasoning extraction with content promotion. Adds an __init__ that reads chat_template_kwargs to decide whether to promote reasoning into the content channel (enable_thinking=False or force_nonempty_content=True), and an extract_reasoning_streaming that mirrors the reasoning delta into the content channel while <think> is still open. Clients that only read the content field receive a non-null value on every delta, while clients that prefer reasoning_content still get the same data on the reasoning channel.

No behavior change for callers that don't pass these chat_template_kwargs.

Rescue whitespace-only content + add streaming reasoning promotionf84fb4b4

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment