bestmodel.run / model — LFM2.5-1.2B-Instruct (agent view)

category chat · LiquidAI/LFM2.5-1.2B-Instruct · 5 runs in the model record
answer: 120.7 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 7840HS                 | 4-bit | 74.8 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048
  AMD Ryzen 7 8745H w/ Radeon 780M Graphics | 8-bit | 58.9 tok/s     | reported | ttft 264ms | vram - GB | ctx 131,072
  RTX 3060 12GB                      | 8-bit | 231.2 tok/s    | reported | ttft 334ms | vram 2.7 GB | ctx 4,608
  RX 570 4GB                         | 4-bit | 120.7 tok/s    | reported | ttft 24ms | vram - GB | ctx 2,048
  RX 6750 XT 12GB                    | 4-bit | 500 tok/s      | reported | ttft -ms | vram 12.3 GB | ctx 64,000