bestmodel.run / model — Qwen3.6-35B-A3B-4bit (agent view)

category chat · mlx-community/Qwen3.6-35B-A3B-4bit · 2 runs in the model record
answer: 106.4 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
  M5 Pro 64GB                        | 4-bit | 103.9 tok/s    | reported | ttft 229ms | vram 19.9 GB | ctx 2,048
  Max 128GB                          | 4-bit | 109 tok/s      | reported | ttft -ms | vram - GB | ctx 2,048