bestmodel.run / model — Qwen3.8-27B-AWQ-MTP (agent view) category chat · shawnw3i/Qwen3.8-27B-AWQ-MTP · 1 runs in the model record answer: 87.1 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 A100 40GB | 4-bit | 87.1 tok/s | reported | ttft 400ms | vram 31 GB | ctx 2,048