Nvidia: 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... Efficient MoE with 30B total / 3B active params Very low latency and cost Strong for agentic and tool-use tasks NVIDIA ecosystem integration Limited deep reasoning capability Below larger Nemotron models Narrower general knowledge Latency-sensitive agent tasks Cost-efficient deployments NVIDIA-optimized inference
Specifications
| Lab | Nvidia |
|---|---|
| Context window | 262,144 |
| Input price | $0.05/1M |
| Output price | $0.20/1M |
| Release | 2025-12-01 00:00:00 |
Strengths
- Efficient MoE with 30B total / 3B active params
- Very low latency and cost
- Strong for agentic and tool-use tasks
- NVIDIA ecosystem integration
Weaknesses
- Limited deep reasoning capability
- Below larger Nemotron models
- Narrower general knowledge
Best for
- Latency-sensitive agent tasks
- Cost-efficient deployments
- NVIDIA-optimized inference
In Depth: Nemotron 3 Nano 30B A3B
Summary
Nemotron 3 Nano 30B A3B is an AI model from Nvidia.
Released 2025-12-01 00:00:00. It currently appears in the Overall category on LMRank. It supports Text input and produces Text output, with a context window of 262.1K tokens. Input pricing is $0.05 per 1M tokens and output is $0.20 per 1M tokens on OpenRouter.