Nemotron-3-Super-120B-A12B
9 records across 2 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 8× B200 | Nemotron-3-Super-120B-A12B | NVFP4 | vLLM | 12686.38 | – | – | – | – | 2026-10-08 | community | – | source |
| 8× B200 | Nemotron-3-Super-120B-A12B | NVFP4 | vLLM | 5274.97 | – | – | – | – | 2026-10-08 | community | – | source |
| 8× B200 | Nemotron-3-Super-120B-A12B | NVFP4 | vLLM | 128.07 | – | – | – | – | 2026-10-08 | community | – | source |
| 8× B200 | Nemotron-3-Super-120B-A12B | NVFP4 | vLLM | 127.98 | – | – | – | – | 2026-10-08 | community | – | source |
| M2 Ultra | Nemotron-3-Super-120B-A12B | 4bit | oMLX | 48.8 | 318.1 | – | – | 1024 | 2026-10-17 | community | – | source |
| M2 Ultra | Nemotron-3-Super-120B-A12B | 4bit | oMLX | 48.1 | 363.1 | – | – | 4096 | 2026-10-17 | community | – | source |
| M2 Ultra | Nemotron-3-Super-120B-A12B | 4bit | oMLX | 47.5 | 369.0 | – | – | 8192 | 2026-10-17 | community | – | source |
| M2 Ultra | Nemotron-3-Super-120B-A12B | 6bit | oMLX | 43.6 | 363.0 | – | – | 1024 | 2026-10-16 | community | – | source |
| M2 Ultra | Nemotron-3-Super-120B-A12B | 6bit | oMLX | 43.5 | 439.6 | – | – | 4096 | 2026-10-16 | community | – | source |