bestmodel.run / model — LFM2.5-350M (agent view)

category chat · LiquidAI/LFM2.5-350M · 12 runs in the model record
answer: 549.9 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
  Radeon AI Pro R9700 32GB           | 4-bit | 539.6 tok/s    | measured | ttft 87ms | vram - GB | ctx 4,096
  RTX 3060 12GB                      | 8-bit | 574.7 tok/s    | reported | ttft 140ms | vram 1.9 GB | ctx 4,608
  RX 5700 XT 8GB                     | 4-bit | 257.3 tok/s    | reported | ttft 76ms | vram - GB | ctx 4,096
  RX 6900 XT 16GB                    | 4-bit | 275.8 tok/s    | reported | ttft 67ms | vram - GB | ctx 4,096
  RX 7900 XTX 24GB                   | 4-bit | 398.4 tok/s    | reported | ttft 57ms | vram - GB | ctx 4,096
  RX 9070 XT 16GB                    | 4-bit | 479.2 tok/s    | reported | ttft 78ms | vram - GB | ctx 4,096
  Ryzen AI Max 395 103GB             | 4-bit | 343.1 tok/s    | reported | ttft 58ms | vram - GB | ctx 4,096