bestmodel.run / model — Qwen2.5-0.5B-Instruct (agent view)

category chat · Qwen/Qwen2.5-0.5B-Instruct · 6 runs in the model record
answer: 263.4 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
  AMD Ryzen 7 7840HS                 | 4-bit | 128.3 tok/s    | reported | ttft -ms | vram - GB | ctx 2,048
  Radeon AI Pro R9700 57GB           | 8-bit | 102.9 tok/s    | reported | ttft 129ms | vram - GB | ctx 2,048
  RTX 3060 12GB                      | 8-bit | 396.2 tok/s    | reported | ttft 201ms | vram 2.4 GB | ctx 4,608
  RTX PRO 6000 Blackwell 96GB        | 8-bit | 1,060.1 tok/s  | reported | ttft -ms | vram 1.8 GB | ctx 4,608