Skip to main content
AI Socratic
Nemotron 3 Nano 30B A3B (free)

NVIDIA released Nemotron 3 Nano 30B A3B (free) on December 4, 2025. The registry currently records it as open weights.

Model publication

Nvidia

Nemotron 3 Nano 30B A3B (free)Open the source for Nemotron 3 Nano 30B A3B (free)

Open weights

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.

Licence
other
Architecture
mixture_of_experts
Parameters
31.6B
Context
256K tokens
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 Hugging Face model card
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 · model preview · Hugging Face model page

Benchmarks

No benchmark observation recorded for this model.

Weightshuggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16Hugging Facehuggingface.coOpenRouteropenrouter.ai2 artifacts in the registry, including third-party rebuilds

About the Authors

A

AI Socratic