Nemotron 3 Nano 30B A3B
NVIDIA🇺🇸
nvidia/nemotron-3-nano-30b-a3bNemotron 3 Nano is NVIDIA's compute-efficient open model in the Nemotron 3 family, a 30B mixture-of-experts model with 3B active parameters. It is optimized for high-throughput, low-cost agentic and multi-agent workloads.
Cost rate
0.1x
Context
262K
Released
Dec 14, 2025
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
No top-ranked categories found.
Performance
Median latency and throughput measured across recent requests.
Throughput177 tok/s
Latency