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

category chat · LiquidAI/LFM2-8B-A1B · 24 runs in the model record
answer: 210.8 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
  GTX 1060 3GB                       | 4-bit | 9.9 tok/s      | reported | ttft 18,068ms | vram - GB | ctx 2,048
  GTX 1060 3GB ×2                    | 4-bit | 18.3 tok/s     | reported | ttft -ms | vram 1.2 GB | ctx 2,048
  RTX 3060 12GB                      | 4-bit | 225.7 tok/s    | measured | ttft 513ms | vram - GB | ctx 131,072