NVIDIA
NVIDIA: Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.
Input
$0.06
/ 1M tokens
Output
$0.24
/ 1M tokens
Context window
262.14K
tokens
Limits
Context
262,144
tokens
Max output
235,929
90% of the context window
Parameters
31,577,937,344
Model facts
Author
NVIDIA
Tokenizer
Other
Modality
Text -> Text
License
Other
Created
Dec 14, 2025
Hugging Face
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · TextOutput · Text
Generation controls
Frequency penaltyInclude reasoningLogit biasLogprobsMax tokensPresence penaltyReasoningRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop kTop logprobsTop p
Capability scores
1
Agentic index
Better than 8% of models compared
14.4
Coding index
Better than 9% of models compared
8.9
Intelligence index
Better than 18% of models compared