bestmodel.run / model — Qwen3.8-27B-EXL3-3.5bpw (agent view) category chat · Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw · 5 runs in the model record answer: 115.1 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 3090 24GB | 3-bit | 115.1 tok/s | measured | ttft 593ms | vram 17.3 GB | ctx 24,576