bestmodel.run / model — Qwen3.6-27b-ROCmFP4-CIRU-CHAOS-SPEED (agent view)

category chat · jcbtc/Qwen3.6-27b-ROCmFP4-CIRU-CHAOS-SPEED · 2 runs in the model record
answer: 92.3 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 128GB             | 4-bit | 132.3 tok/s    | reported | ttft 105ms | vram - GB | ctx 2,048
  Ryzen AI Max 395 128GB             | 16-bit | 52.2 tok/s     | reported | ttft 339ms | vram - GB | ctx 2,048