bestmodel.run / model — LFM2.5-8B-A1B (agent view)

category chat · LiquidAI/LFM2.5-8B-A1B · 36 runs in the model record
answer: 189 tok/s (model median)

Honesty ladder: measured > reported > extrapolated > formula > no data yet.
Empty fields stay empty — never filled with an estimate.

  rig | quant | median result | basis | ttft | peak vram | max context
  AMD Ryzen 7 8745H w/ Radeon 780M Graphics | 4-bit | 63.1 tok/s     | reported | ttft 521ms | vram - GB | ctx 65,536
  GTX 1060 3GB                       | 4-bit | 8.5 tok/s      | reported | ttft 33,535ms | vram - GB | ctx 2,048
  M5 Pro 48GB                        | 4-bit | 189.3 tok/s    | reported | ttft 134ms | vram 4.8 GB | ctx 2,048
  Radeon AI Pro R9700 34GB           | 4-bit | 241.1 tok/s    | reported | ttft 194ms | vram 5.4 GB | ctx 4,096
  RTX 3060 12GB                      | 4-bit | 194.4 tok/s    | measured | ttft 323ms | vram 6.9 GB | ctx 131,072
  RTX 3060 12GB                      | 8-bit | 128.5 tok/s    | reported | ttft 37ms | vram - GB | ctx 4,096
  RTX 5060 Ti 16GB                   | 4-bit | 254.3 tok/s    | reported | ttft 22ms | vram - GB | ctx 4,096
  RTX 5060 Ti 16GB                   | 8-bit | 183.1 tok/s    | reported | ttft 25ms | vram - GB | ctx 4,096
  RTX 5070 Ti 16GB                   | 4-bit | 402.3 tok/s    | reported | ttft 16ms | vram - GB | ctx 4,096
  RTX 5070 Ti 16GB                   | 8-bit | 307.4 tok/s    | reported | ttft 20ms | vram - GB | ctx 4,096
  RX 570 4GB                         | 4-bit | 76 tok/s       | reported | ttft 31,168ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 18.6 tok/s     | measured | ttft 325ms | vram - GB | ctx 2,048
  RX 6700 10GB                       | 4-bit | 172.3 tok/s    | reported | ttft 2,151ms | vram 4 GB | ctx 4,096