NVIDIA: Nemotron 3 Nano 30B A3B
NVIDIA's Nemotron 3 Nano 30B A3B offers strong math and instruction-following performance at a very competitive price, making it good value for structured tasks and tool-use workflows. Its reasoning and coding scores are more modest, but the overall value proposition is compelling for cost-conscious deployments.
Assessment date: March 14, 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 |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.05 | $0.000050 |
| Output | $0.20 | $0.000200 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
