bestmodel.run / model — Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx (agent view)

category chat · Brooooooklyn/Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx · 1 runs in the model record
answer: 83.4 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 Max 64GB                        | 8-bit | 83.4 tok/s     | reported | ttft 106ms | vram 22 GB | ctx 262,144