Nemotron 3 NanoOpen Source

Released

Nemotron 3 Nano is an AI model released by NVIDIA on Monday, Dec 15 2025, 119 days after Nemotron Nano 2. It is an open-source model — weights, and training code/data, released under an open license. It is a 30B parameter model. Benchmark results (shown below) cover BullshitBench v2, LiveCodeBench, and GPQA Diamond.

Available from

Novita$0.05$0.20256Kfp4
Nebius$0.06$0.24256Kfp8
USD per 1M tokens

Benchmarks

Coding

LiveCodeBench
68.3%
#11 of 12

Reasoning & science

GPQA Diamond
73%
#46 of 59

Robustness

BullshitBench v2
28%
#59 of 94

Compare Nemotron 3 Nano with

Nemotron 3 Nano

About

Nemotron 3 Nano, released December 15, 2025, opened NVIDIA's first fully in-house Nemotron generation — no Llama base underneath — and made the architectural bet explicit: a hybrid of Mamba-2 state-space layers, mixture-of-experts feed-forwards and a small number of attention layers, with 30 billion total parameters and roughly 3.5 billion active per token. The design traded a little per-token capacity for throughput on long agentic transcripts, which is what NVIDIA said models would spend 2026 doing.

Its launch card reported 73.0% on GPQA Diamond, 68.3% on LiveCodeBench and 89.1% on AIME 2025 without tools — unusually strong mathematics for the size — and the release was open in the fullest sense the industry used: weights, the bulk of the datasets and the training recipes all published. Super and Ultra tiers were promised for 2026 and arrived in March and June of that year.

Frequently asked questions

Nemotron 3 Nano was released by NVIDIA on Monday, Dec 15 2025.

All NVIDIA releases

9 tracked