← All models

nvidia

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.

Try in playgroundAPI reference
262,144 context
Modalities:text->text
Released:12/14/2025

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.

Weekly tokens

3.7B

Tokens generated this week (network-wide)

Usage by period

Today752.9M tokens
This week5.8B tokens
This month28.1B tokens
Trending5.8B tokens