bestmodel.run / model — Ternary-Bonsai-27B-mlx-2bit (agent view)

category chat · prism-ml/Ternary-Bonsai-27B-mlx-2bit · 1 runs in the model record
answer: 12.7 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
  M4 16GB                            | 1-bit | 12.7 tok/s     | reported | ttft -ms | vram 9.9 GB | ctx 4,096