Nemotron 3 Nano 30B A3B

Nvidia llm

Small hybrid Mamba-2 and Transformer mixture-of-experts reasoning model with a toggleable thinking mode and a 1M-token context.

overall ⌄

33.2

109 of 125 ranked

price · $/M tokens

self-hosted

open weights, no first-party API

to run it yourself ⌄

18 GB

minimum · 72 GB recommended

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmarkpublishedmeasured
MMLU-Pro78.3 —
AIME 202589.1 —
SWE-bench38.8 —
HLE10.6 —

Lineage

No recorded lineage — root or standalone model.

view in full graph →

Metadata

orgNvidia
released2025-12-15
params30B-A3B
licensenvidia-open-model
hf idnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16