Skip to content
NVIDIA

Nemotron 3 Nano 30B A3B

flagship
NVIDIA · released 2025-06-01 · text->text
currently routing · 4.2k rpm
262K tokens
Context
$0.05 / 1M
Input
$0.20 / 1M
Output
— t/s
Speed
open
License
/ ABOUT

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.

BENCHMARKS Artificial Analysis Index
Intelligence 24.3
Coding 19
Agentic 19.1

Providers for Nemotron 3 Nano 30B A3B

3 routes · sorted by uptime

ClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.

Provider
Context
Quant
Uptime · 30d
262K
bf16
0.00%
262K
bf16
0.00%
262K
bf16
0.00%