bestmodel.run / model — LFM2.5-2.6B-GGUF (agent view)

category chat · LiquidAI/LFM2.5-2.6B-GGUF · 2 runs in the model record
answer: 219 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
  Arc Pro B70 32GB                   | 8-bit | 132.4 tok/s    | reported | ttft -ms | vram - GB | ctx 8,192
  RTX 3090 24GB                      | 4-bit | 305.6 tok/s    | reported | ttft 37ms | vram 2.3 GB | ctx 24,576