bestmodel.run / model — Qwen3.8-27B-W4A16-AutoRound (agent view)

category chat · dbirks/Qwen3.8-27B-W4A16-AutoRound · 14 runs in the model record
answer: 187.5 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
  CMP 170HX 64GB                     | 4-bit | 255.9 tok/s    | measured | ttft 440ms | vram 56.5 GB | ctx 131,072
  RTX 3090 24GB ×2                   | 4-bit | 182.4 tok/s    | measured | ttft 825ms | vram 44.4 GB | ctx 262,144