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

category chat · unsloth/Qwen3.5-9B · 2 runs in the model record
answer: 37.6 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
  Ryzen AI Max 395 64GB              | 4-bit | 38.1 tok/s     | reported | ttft 1,712ms | vram 5.7 GB | ctx 8,192