bestmodel.run / model — Bonsai-27B-mlx-1bit (agent view)

category chat · prism-ml/Bonsai-27B-mlx-1bit · 1 runs in the model record
answer: 21.6 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
  M4 16GB                            | 1-bit | 21.6 tok/s     | reported | ttft -ms | vram 4.5 GB | ctx 4,096