NVIDIA Nemotron 3.5 Lightning
92 records across 6 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 164.4 | 3556.0 | – | – | 1024 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 163.8 | 3560.0 | – | – | 1024 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 163.8 | 3560.0 | – | – | 1024 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 161.3 | 1643.0 | – | – | 4096 | 2026-10-17 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 158.5 | 4070.0 | – | – | 4096 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 157.9 | 4070.0 | – | – | 4096 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 157.9 | 4070.0 | – | – | 4096 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 152.6 | 4002.0 | – | – | 8192 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 152.6 | 4002.0 | – | – | 8192 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 152.2 | 3826.0 | – | – | 16384 | 2026-10-17 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 148.1 | 1535.0 | – | – | 4096 | 2026-10-15 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 146.9 | 1615.0 | – | – | 4096 | 2026-10-15 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 145.2 | 1876.0 | – | – | 4096 | 2026-10-07 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 144.3 | 2404.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 143.6 | 2877.0 | – | – | 1024 | 2026-10-12 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 143.6 | 2877.0 | – | – | 1024 | 2026-10-12 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 143.2 | 2604.0 | – | – | 8192 | 2026-10-16 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 142.9 | 2312.0 | – | – | 1024 | 2026-10-12 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 142.3 | 4221.0 | – | – | 8192 | 2026-10-12 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 142.3 | 4221.0 | – | – | 8192 | 2026-10-12 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 140.3 | 2525.0 | – | – | 4096 | 2026-10-12 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 139.5 | 1233.0 | – | – | 1024 | 2026-10-15 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 139.4 | 2499.0 | – | – | 16384 | 2026-10-16 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 139.1 | 3380.0 | – | – | 16384 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 139.1 | 3380.0 | – | – | 16384 | 2026-10-07 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 136.6 | 1486.0 | – | – | 16384 | 2026-10-15 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 136.4 | 2507.0 | – | – | 8192 | 2026-10-12 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 135.6 | 2124.0 | – | – | 4096 | 2026-10-07 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 135.1 | 1953.0 | – | – | 16384 | 2026-10-07 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 134.1 | 1503.0 | – | – | 16384 | 2026-10-15 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 130.2 | 3947.0 | – | – | 16384 | 2026-10-12 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 130.2 | 3947.0 | – | – | 16384 | 2026-10-12 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 130.1 | 4192.0 | – | – | 4096 | 2026-10-12 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 130.1 | 4192.0 | – | – | 4096 | 2026-10-12 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 127.1 | 4065.0 | – | – | 16384 | 2026-10-07 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 126.8 | 1563.0 | – | – | 4096 | 2026-10-09 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 126.8 | 1563.0 | – | – | 4096 | 2026-10-09 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 124.1 | 2439.0 | – | – | 8192 | 2026-10-13 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 123.3 | 960.7 | – | – | 8192 | 2026-10-15 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 122.6 | 980.1 | – | – | 4096 | 2026-10-15 | community | contradiction | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 122.3 | 1491.0 | – | – | 4096 | 2026-10-08 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 122.2 | 3159.0 | – | – | 32768 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 122.2 | 3159.0 | – | – | 32768 | 2026-10-07 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 120.2 | 941.8 | – | – | 16384 | 2026-10-15 | community | contradiction | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 118.9 | 1308.0 | – | – | 16384 | 2026-10-09 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 118.9 | 1308.0 | – | – | 16384 | 2026-10-09 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 117.6 | 2288.0 | – | – | 1024 | 2026-10-13 | community | contradiction | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 117.0 | 2401.0 | – | – | 16384 | 2026-10-13 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 113.8 | 2357.0 | – | – | 4096 | 2026-10-13 | community | contradiction | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 113.1 | 3687.0 | – | – | 32768 | 2026-10-12 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 113.1 | 3687.0 | – | – | 32768 | 2026-10-12 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 109.4 | 2223.0 | – | – | 32768 | 2026-10-13 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 106.0 | 1253.0 | – | – | 1024 | 2026-10-08 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 100.2 | 2796.0 | – | – | 65536 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 100.2 | 2796.0 | – | – | 65536 | 2026-10-07 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 97.8 | 1328.0 | – | – | 1024 | 2026-10-09 | community | – | source |
| M4 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 97.8 | 1328.0 | – | – | 1024 | 2026-10-09 | community | – | source |
| M3 Ultra | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 96.5 | 1501.0 | – | – | 131072 | 2026-10-12 | community | – | source |
| M4 Pro | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 96.5 | 715.1 | – | – | 1024 | 2026-10-16 | community | – | source |
| M4 Pro | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 95.7 | 761.1 | – | – | 1024 | 2026-10-16 | community | – | source |
| M4 Pro | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 94.7 | 649.7 | – | – | 1024 | 2026-10-10 | community | – | source |
| M4 Pro | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 94.7 | 675.7 | – | – | 1024 | 2026-10-18 | community | – | source |
| M4 Pro | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 94.2 | 802.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M4 Pro | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 94.2 | 797.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M4 Pro | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 93.3 | 645.8 | – | – | 1024 | 2026-10-11 | community | – | source |
| M4 Pro | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 93.2 | 700.8 | – | – | 4096 | 2026-10-18 | community | – | source |
| M4 Pro | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 91.5 | 680.3 | – | – | 4096 | 2026-10-11 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 91.2 | 2830.0 | – | – | 65536 | 2026-10-12 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 91.2 | 2830.0 | – | – | 65536 | 2026-10-12 | community | – | source |
| M1 Ultra | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 90.3 | 826.9 | – | – | 1024 | 2026-10-16 | community | – | source |
| M1 Ultra | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 87.6 | 1038.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 87.1 | 720.0 | – | – | 4096 | 2026-10-10 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 84.6 | 2332.0 | – | – | 131072 | 2026-10-07 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 81.1 | 677.8 | – | – | 1024 | 2026-10-10 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 77.6 | 675.9 | – | – | 16384 | 2026-10-10 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 73.7 | 2281.0 | – | – | 131072 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 73.7 | 2281.0 | – | – | 131072 | 2026-10-07 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 71.5 | 673.7 | – | – | 1024 | 2026-10-10 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ6e | oMLX | 68.8 | 870.4 | – | – | 1024 | 2026-10-10 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ6e | oMLX | 68.5 | 643.3 | – | – | 1024 | 2026-10-08 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 68.2 | 717.7 | – | – | 8192 | 2026-10-10 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ6e | oMLX | 67.9 | 850.4 | – | – | 1024 | 2026-10-08 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ6e | oMLX | 67.6 | 632.6 | – | – | 1024 | 2026-10-08 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ6e | oMLX | 62.9 | 934.4 | – | – | 4096 | 2026-10-10 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ6e | oMLX | 62.3 | 677.1 | – | – | 16384 | 2026-10-08 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ6e | oMLX | 62.0 | 883.5 | – | – | 16384 | 2026-10-08 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ6e | oMLX | 61.2 | 677.2 | – | – | 16384 | 2026-10-08 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ6e | oMLX | 59.6 | 884.7 | – | – | 16384 | 2026-10-10 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 57.0 | 1886.0 | – | – | 199680 | 2026-10-07 | community | – | source |
| M5 Max | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 57.0 | 1886.0 | – | – | 199680 | 2026-10-07 | community | – | source |
| M2 Max | NVIDIA Nemotron 3.5 Lightning | oQ4e | oMLX | 53.7 | 627.7 | – | – | 32768 | 2026-10-10 | community | – | source |
| M4 Pro | NVIDIA Nemotron 3.5 Lightning | 4bit | oMLX | 32.2 | 682.2 | – | – | 4096 | 2026-10-10 | community | contradiction | source |