bestmodel.run / model — Qwen3.6-27B-UD-MLX-6bit (agent view)

category chat · unsloth/Qwen3.6-27B-UD-MLX-6bit · 1 runs in the model record
answer: 13 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
  Max 128GB                          | 6-bit | 13 tok/s       | reported | ttft -ms | vram 60.3 GB | ctx 2,048