bestmodel.run / model — Qwen3.6-35B-A3B-int4-ov (agent view) category chat · OpenVINO/Qwen3.6-35B-A3B-int4-ov · 1 runs in the model record answer: 11.1 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 Arc B580 12GB | 4-bit | 11.1 tok/s | reported | ttft -ms | vram 9.2 GB | ctx 262,144