models · nvidia
NVIDIA Nemotron 3 Nano 30B A3B — catalogued from third-party evaluation data; no weights held by Sovereign Frontier.
| Method | third-party-report |
|---|
| Publisher | nvidia |
|---|---|
| Origin | United States |
| Licence | NVIDIA-Open-Model |
| Pulls recorded here | 6 |
| MMLU-Pro | 57.9 |
|---|---|
| GPQA Diamond | 39.9 |
| AIME 2025 | 13.3 |
| LiveCodeBench | 36 |
| IFBench | 37.5 |
| Humanity's Last Exam | 4.6 |
Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.
| Hardware | Build measured | Decode @ 8K | Memory @ 8K | Decode mode |
|---|---|---|---|---|
| NVIDIA GeForce RTX 5090 32GB | NVFP4 | 417 tok/s | 30.4 GB | ordinary |
| NVIDIA RTX PRO 6000 Blackwell 96GB | NVFP4 | 317 tok/s | 90.6 GB | ordinary |
| NVIDIA RTX PRO 6000 Blackwell 96GB | FP8 | 254 tok/s | 90.3 GB | ordinary |
| NVIDIA RTX 6000 Ada 48GB | NVFP4 | 219 tok/s | 45.6 GB | ordinary |
| NVIDIA RTX 6000 Ada 48GB | FP8 | 187 tok/s | 45.4 GB | ordinary |
| NVIDIA DGX Spark 128GB | NVFP4 | 60.5 tok/s | 54.7 GB | ordinary |
| NVIDIA DGX Spark 128GB | FP8 | 44.1 tok/s | 112.6 GB | ordinary |
| MacBook Pro M5 Max 128GB · 40-core GPU | NVFP4 | 109 tok/s | 22.9 GB | not stated |
Measured by local.ai, not by us: 13 runs, 5 more not listed. Each names its engine pinned by image digest and the exact serve command, in the full record.
Registry record as of 2026-07-26. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.