bestmodel.run / model — Qwen3.6-27B-AWQ-INT4 (agent view) category chat · drawais/Qwen3.6-27B-AWQ-INT4 · 3 runs in the model record answer: 6.4 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 3060 12GB ×2 | 4-bit | 6.4 tok/s | measured | ttft 659ms | vram 22.4 GB | ctx 814