Back to Leaderboard

NVIDIA: Nemotron 3 Nano 30B A3B

Developed by nvidia

API Pricing (per 1M tokens)

Input$0.05
Output$0.20

Intelligence Benchmarks

MMLU Pro57.9%
GPQA39.9%
Intelligence Index13.3
LivebenchN/A

Technical Specifications

Context Window262K Tokens
Vision SupportNo
Tokens per Second120
Time to First Token (s)0.23
Modalities
text->text

About 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. Note: For the free endpoint, all prompts and output are logged to improve the provider's model and its product and services. Please do not upload any personal, confidential, or otherwise sensitive information. This is a trial use only. Do not use for production or business-critical systems.