nvidia
/

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Text Generation

Model card Files Files and versions

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

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

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
```

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Commit History

Update README.md

cbd3fa9
verified

suhara commited on Mar 15

Upload modeling_nemotron_h.py (#53)

5a48de7

suhara commited on Feb 20

Remove Reference to Feature Voting (#49)

378df16

Chris-Alexiuk commited on Feb 5

Add community evaluation results for GPQA, HLE, MMLU-PRO (#39)

6afd24e
verified

nielsr HF Staff commited on Jan 18

Add vLLM example w/ 1M context length (#38)

52469ad
verified

suhara commited on Jan 8

Update README.md (#18)

eb82b63
verified

suhara commited on Jan 8

Update config.json (#37)

b4e3030
verified

suhara commited on Jan 8

Update README.md

00bd6d1
verified

suhara commited on Jan 8

Update README.md

7573cfb
verified

suhara commited on Jan 8

Update README.md

af5231a
verified

suhara commited on Jan 6

Update README.md (#35)

81d6214
verified

suhara commited on Jan 6

Update License Shield (#33)

2e43387
verified

llm-wizard commited on Dec 23, 2025

Update License (#32)

ad735b6
verified

llm-wizard commited on Dec 23, 2025

Adding Generic Reasoning Budget (#23)

0c547ff
verified

llm-wizard commited on Dec 19, 2025

Update README.md (#19)

d3ad469
verified

suhara commited on Dec 18, 2025

Add Links to Data Designer (#16)

d011723
verified

llm-wizard commited on Dec 18, 2025

Add References to Data Designer. (#11)

40f3871
verified

llm-wizard commited on Dec 17, 2025

Add reference to Technical Report (#10)

cda2b16
verified

llm-wizard commited on Dec 17, 2025

Update README.md

fcd023f
verified

suhara commited on Dec 15, 2025

Update README.md (#6)

d8abe0b
verified

suhara commited on Dec 15, 2025

Update README.md

eab7377
verified

suhara commited on Dec 15, 2025

Update README.md

fdb60b2
verified

suhara commited on Dec 15, 2025

Update README.md

96133d5
verified

bkartal commited on Dec 15, 2025

Upload notebook.ipynb (#1)

13a81c2
verified

burtenshaw HF Staff commited on Dec 15, 2025

Upload local_nvidia_nemotron_3_nano_30b_a3b.yaml

11a4bf9
verified

suhara commited on Dec 15, 2025

Update README.md

904e330
verified

suhara commited on Dec 15, 2025

Create README.md

22d14e6
verified

suhara commited on Dec 15, 2025

Upload 4 files

998adf5
verified

suhara commited on Dec 15, 2025

Upload accuracy_chart.png

3c31432
verified

suhara commited on Dec 15, 2025

Upload 2 files

4fed69b
verified

suhara commited on Dec 15, 2025

Upload modeling_nemotron_h.py

4a31ff1
verified

suhara commited on Dec 15, 2025

Upload modeling_nemotron_h.py

0d1698d
verified

suhara commited on Dec 13, 2025

Upload nano_v3_reasoning_parser.py

f6aca92
verified

suhara commited on Dec 12, 2025

Upload folder using huggingface_hub

a7d6c57
verified

suhara commited on Dec 4, 2025

initial commit

b8a2d7d
verified

suhara commited on Dec 4, 2025