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...
The figures
- Made by
- NVIDIA
- Model ID
- nvidia/nemotron-3-nano-30b-a3b
- Input
- $0.05 per million tokens
- Output
- $0.2 per million tokens
- Context window
- 262K tokens
- Longest answer
- 236K tokens
- Takes in
- text
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- No
- Open weights
- Yes
- Released
- 14 Dec 2025
Read on 3 Oct 2026.