Nemotron-Cascade-2-30B-A3B
24 records across 4 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 Pro | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 93.6 | 634.1 | – | – | 1024 | 2026-10-11 | community | – | source |
| M4 Pro | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 93.6 | 634.1 | – | – | 1024 | 2026-10-11 | community | – | source |
| M4 Pro | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 88.2 | 629.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| M4 Pro | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 88.2 | 629.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 71.4 | 786.7 | – | – | 1024 | 2026-10-08 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 70.3 | 743.2 | – | – | 1024 | 2026-10-07 | community | – | source |
| M1 Max | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 66.6 | 479.7 | – | – | 1024 | 2026-10-07 | community | – | source |
| M1 Max | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 65.0 | 542.5 | – | – | 4096 | 2026-10-07 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 64.1 | 691.7 | – | – | 4096 | 2026-10-08 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 62.8 | 655.2 | – | – | 4096 | 2026-10-07 | community | – | source |
| M1 Max | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 62.5 | 533.5 | – | – | 8192 | 2026-10-07 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 60.7 | 632.8 | – | – | 8192 | 2026-10-07 | community | – | source |
| M6 | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 59.5 | 1239.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M6 | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 59.4 | 1109.0 | – | – | 1024 | 2026-10-16 | community | – | source |
| M1 Max | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 59.1 | 506.8 | – | – | 16384 | 2026-10-07 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 59.1 | 629.1 | – | – | 16384 | 2026-10-08 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 57.2 | 657.2 | – | – | 8192 | 2026-10-08 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 54.4 | 593.4 | – | – | 32768 | 2026-10-07 | community | – | source |
| M1 Max | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 51.9 | 461.7 | – | – | 32768 | 2026-10-07 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 50.4 | 646.9 | – | – | 16384 | 2026-10-07 | community | contradiction | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 47.0 | 530.3 | – | – | 65536 | 2026-10-07 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 46.0 | 488.2 | – | – | 65536 | 2026-10-08 | community | – | source |
| M2 Max | Nemotron-Cascade-2-30B-A3B | mxfp8 | oMLX | 43.1 | 568.8 | – | – | 32768 | 2026-10-08 | community | contradiction | source |
| M1 Max | Nemotron-Cascade-2-30B-A3B | 4bit | oMLX | 39.9 | 392.0 | – | – | 65536 | 2026-10-07 | community | – | source |