NVIDIA
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
NVIDIA Nemotron 3 Nano is an open reasoning model optimized for fast, cost-efficient inference. Built with a hybrid MoE and Mamba architecture and trained on NVIDIA-curated synthetic reasoning data, it delivers strong multi-step reasoning with stable latency and predictable performance for agentic and production workloads.
NVIDIA model catalogModel Snapshot
TypeLanguage
ReleaseDec 1, 2024
Context262,144
Tagsreasoning
Overall
Rank #379 across 523
13.2
Coding
Rank #253 across 433
15.8
Blended Price
Rank #20 across 355
$0.088/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed87.3 tok/s
First Token0.26s
Max Output262,144
Pricing
Blended$0.088/M
Input$0.050/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 13.2 | #379 |
| Artificial Analysis Coding Index | coding | 15.8 | #253 |
| Artificial Analysis Math Index | math | 13.3 | #226 |
| MMLU-Pro | reasoning | 57.9% | #273 |