bestmodel.run / model — Qwen3.8-Flash-Next-FP8 (agent view) category chat · Qwen/Qwen3.8-Flash-Next-FP8 · 12 runs in the model record answer: 32.4 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 Arc Pro B70 32GB ×4 | 8-bit | 32.4 tok/s | measured | ttft 549ms | vram - GB | ctx 4,352