NVIDIA: Nemotron 3 Nano 30B A3B
8.1 / 10
262.1K context
Proprietary
About this model
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...
Benchmark Scores
MMMU
82.9
Aider
81.3
MATH-500
98.1
MMLU-Pro
85.6
SimpleQA
49.4
AIME-2024
91.6
Technical Specs
- Architecture: text->text
- Context Window: 262,144 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 0.05 / 1M tokens | 0.2 / 1M tokens | USD |