bestmodel.run / model — Qwen3-VL-8B-Instruct (agent view)

category chat · Qwen/Qwen3-VL-8B-Instruct · 2 runs in the model record
answer: 89.8 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
  Radeon AI Pro R9700 32GB ×3        | 8-bit | 58.8 tok/s     | reported | ttft 174ms | vram 15.5 GB | ctx 786
  RX 7900 XTX 24GB                   | 8-bit | 89.8 tok/s     | reported | ttft 201ms | vram - GB | ctx 8,192