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

category chat · philbert440/Qwen3.8-27B-W4A16-AWQ · 6 runs in the model record
answer: 103 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
  RTX 5090 32GB                      | 4-bit | 103 tok/s      | measured | ttft -ms | vram - GB | ctx 2,048