bestmodel.run / model — Qwen3.5-9B-4bit (agent view)

category chat · mlx-community/Qwen3.5-9B-4bit · 1 runs in the model record
answer: 33 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
  M2 Pro 16GB                        | 4-bit | 33 tok/s       | reported | ttft 1,400ms | vram - GB | ctx 4,096