bestmodel.run / model — Qwopus3.8-27B-Flash (agent view) category chat · Jackrong/Qwopus3.8-27B-Flash · 2 runs in the model record answer: 21.3 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 | 15.6 tok/s | reported | ttft 2,053ms | vram - GB | ctx 790