NVIDIA: Nemotron 3 Nano 30B A3B (free)
The free tier of NVIDIA's Nemotron 3 Nano 30B A3B has no benchmark data of its own and must be scored conservatively. Tool use support and a 256K context window are useful, but businesses should refer to the paid variant's benchmarks before committing to this model.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
| Parameters | 30B |
Model Information
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
