bestmodel.run / model — Qwen3.8-27B-exl3 (agent view) category chat · turboderp/Qwen3.8-27B-exl3 · 4 runs in the model record answer: 71.9 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 5070 12GB | 3-bit | 71.9 tok/s | measured | ttft 2,364ms | vram 10 GB | ctx 126,976