bestmodel.run / model — BTL-3-Compact (agent view)

category chat · badtheorylabs/BTL-3-Compact · 2 runs in the model record
answer: 3.8 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
  M1 Max 64GB                        | 2-bit | 3.8 tok/s      | reported | ttft 107,563ms | vram - GB | ctx 2,048