NVIDIA-Nemotron-3-Nano-30B-A3B
4 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M5 Pro | NVIDIA-Nemotron-3-Nano-30B-A3B | 4bit | oMLX | 102.6 | 1950.0 | – | – | 1024 | 2026-10-10 | community | – | source |
| M5 Pro | NVIDIA-Nemotron-3-Nano-30B-A3B | 4bit | oMLX | 100.1 | 1872.0 | – | – | 1024 | 2026-10-10 | community | – | source |
| M5 Pro | NVIDIA-Nemotron-3-Nano-30B-A3B | 4bit | oMLX | 98.6 | 1901.0 | – | – | 1024 | 2026-10-10 | community | – | source |
| M5 Pro | NVIDIA-Nemotron-3-Nano-30B-A3B | 4bit | oMLX | 86.8 | 1635.0 | – | – | 1024 | 2026-10-09 | community | contradiction | source |