Instructions to use nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-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-Nano-30B-A3B-BF16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", trust_remote_code=True)
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
Local Apps Settings

vLLM

How to use nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-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-Nano-30B-A3B-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-Nano-30B-A3B-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

SGLang

How to use nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-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-Nano-30B-A3B-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-Nano-30B-A3B-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-Nano-30B-A3B-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-Nano-30B-A3B-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 with Docker Model Runner:
```
docker model run hf.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
```

suhara commited on Dec 15, 2025

Commit

904e330

verified ·

1 Parent(s): 22d14e6

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -195,7 +195,7 @@ Stage 3: Reinforcement Learning
 NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 model is a result of the above work.
-The end-to-end training recipe is available in the [NVIDIA Nemotron Developer Repository](https://github.com/NVIDIA-NeMo/Nemotron). Evaluation results can be replicated using the [NeMo Evaluator SDK](https://github.com/NVIDIA-NeMo/Evaluator). More details on the datasets and synthetic data generation methods can be found in the technical report [NVIDIA Nemotron Nano v3](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Nano-Technical-Report.pdf).
 ## Input
@@ -400,7 +400,7 @@ For all domains, we apply a unified data filtering pipeline to ensure that only
 Alongside the model, we release our final [pre-training](https://huggingface.co/collections/nvidia/nemotron-pre-training-datasets) and [post-training](https://huggingface.co/collections/nvidia/nemotron-post-training-v3) data, as outlined in this section. For ease of analysis, there is a sample set that is ungated. For all remaining code, math and multilingual data, gating and approval is required, and the dataset is permissively licensed for model training purposes.
-More details on the datasets and synthetic data generation methods can be found in the technical report [NVIDIA Nemotron Nano v3](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Nano-Technical-Report.pdf).
 | Dataset | Collection Period |
 | :---- | :---- |
@@ -588,7 +588,7 @@ The GitHub Crawl was collected using the GitHub REST API and the Amazon S3 API.
 ## Training Dataset
-| Dataset | \# of Tokens in Nemotron Nano 2 | \# of Tokens in Nemotron Nano 3 |
 | :---- | :---- | :---- |
 | English Common Crawl | 3,360,110,334,818 | 3,456,523,212,210 |
 | English Synthetic CC | 1,949,464,641,123 | 4,340,740,677,920 |

 NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 model is a result of the above work.
+The end-to-end training recipe is available in the [NVIDIA Nemotron Developer Repository](https://github.com/NVIDIA-NeMo/Nemotron). Evaluation results can be replicated using the [NeMo Evaluator SDK](https://github.com/NVIDIA-NeMo/Evaluator). More details on the datasets and synthetic data generation methods can be found in the technical report [NVIDIA Nemotron 3 Nano](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Nano-Technical-Report.pdf).
 ## Input
 Alongside the model, we release our final [pre-training](https://huggingface.co/collections/nvidia/nemotron-pre-training-datasets) and [post-training](https://huggingface.co/collections/nvidia/nemotron-post-training-v3) data, as outlined in this section. For ease of analysis, there is a sample set that is ungated. For all remaining code, math and multilingual data, gating and approval is required, and the dataset is permissively licensed for model training purposes.
+More details on the datasets and synthetic data generation methods can be found in the technical report [NVIDIA Nemotron 3 Nano](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Nano-Technical-Report.pdf).
 | Dataset | Collection Period |
 | :---- | :---- |
 ## Training Dataset
+| Dataset | \# of Tokens in Nemotron Nano 2 | \# of Tokens in Nemotron 3 Nano |
 | :---- | :---- | :---- |
 | English Common Crawl | 3,360,110,334,818 | 3,456,523,212,210 |
 | English Synthetic CC | 1,949,464,641,123 | 4,340,740,677,920 |