bestmodel.run / model — Qwen3.5-9B-TT-BFP4-P150 (agent view) category chat · Lottolabs/Qwen3.5-9B-TT-BFP4-P150 · 1 runs in the model record answer: 76.2 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 Tenstorrent P150 32GB | 4-bit | 76.2 tok/s | reported | ttft 209ms | vram - GB | ctx 8,192