NVIDIA-Nemotron-3.5-Bolt-74B-A9B
35 records across 3 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 75.4 | 949.9 | – | – | 1024 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 75.4 | 949.9 | – | – | 1024 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 74.5 | 946.0 | – | – | 1024 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 73.7 | 1032.0 | – | – | 4096 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 73.7 | 1032.0 | – | – | 4096 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 73.3 | 802.4 | – | – | 1024 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 72.8 | 1078.0 | – | – | 4096 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 72.6 | 1070.0 | – | – | 8192 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 71.8 | 1053.0 | – | – | 8192 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 71.2 | 1045.0 | – | – | 16384 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 71.0 | 1044.0 | – | – | 4096 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 69.6 | 990.7 | – | – | 32768 | 2026-10-18 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 68.9 | 1045.0 | – | – | 16384 | 2026-10-18 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 60.5 | 585.6 | – | – | 1024 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 60.4 | 597.8 | – | – | 4096 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 59.4 | 548.2 | – | – | 8192 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 56.6 | 521.7 | – | – | 16384 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | 5bit | oMLX | 54.3 | 517.2 | – | – | 1024 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 54.1 | 486.4 | – | – | 32768 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | 5bit | oMLX | 54.1 | 495.0 | – | – | 1024 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | 5bit | oMLX | 54.1 | 552.1 | – | – | 4096 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | 5bit | oMLX | 53.6 | 552.0 | – | – | 4096 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 40.7 | 389.1 | – | – | 65536 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 35.4 | 313.3 | – | – | 131072 | 2026-10-17 | community | – | source |
| M3 Ultra | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | unknown | oMLX | 31.9 | 963.4 | – | – | 32768 | 2026-10-18 | community | contradiction | source |
| M1 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | oQ4e | oMLX | 27.9 | 238.2 | – | – | 1024 | 2026-10-16 | community | – | source |
| M1 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | oQ4e | oMLX | 27.6 | 248.1 | – | – | 4096 | 2026-10-16 | community | – | source |
| M1 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | oQ4e | oMLX | 27.3 | 249.4 | – | – | 4096 | 2026-10-16 | community | – | source |
| M1 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | oQ4e | oMLX | 27.2 | 241.7 | – | – | 1024 | 2026-10-16 | community | – | source |
| M1 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | oQ4e | oMLX | 26.2 | 247.8 | – | – | 8192 | 2026-10-16 | community | – | source |
| M1 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | oQ4e | oMLX | 25.3 | 243.2 | – | – | 16384 | 2026-10-16 | community | – | source |
| M1 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | oQ4e | oMLX | 23.9 | 231.7 | – | – | 32768 | 2026-10-16 | community | – | source |
| M1 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | oQ4e | oMLX | 21.3 | 214.1 | – | – | 65536 | 2026-10-16 | community | – | source |
| M1 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | oQ4e | oMLX | 17.9 | 184.8 | – | – | 131072 | 2026-10-16 | community | – | source |
| M1 Max | NVIDIA-Nemotron-3.5-Bolt-74B-A9B | oQ4e | oMLX | 15.2 | 159.1 | – | – | 199680 | 2026-10-16 | community | – | source |