NVIDIA logo

NVIDIA

Nemotron 3 Nano 30B A3B (free)

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...

Input / 1M tokens
Free
Output / 1M tokens
Free
Context window
256K tokens
Provider
NVIDIA

Performance

Median streaming throughput and first-token latency measured by Artificial Analysis.

Output tokens / sec
Time to first token