bestmodel.run / model — Qwen3-VL-2B-Instruct (agent view)

category chat · Qwen/Qwen3-VL-2B-Instruct · 1 runs in the model record
answer: 27.9 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
  Orin Nano Super Developer Kit 8GB  | 4-bit | 27.9 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048