bestmodel.run / model — Qwen3-4B (agent view)

category chat · Qwen/Qwen3-4B · 17 runs in the model record
answer: 55.2 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
  Arc Pro B60 24GB                   | 4-bit | 76 tok/s       | reported | ttft 265ms | vram - GB | ctx 2,048
  Arc Pro B70 32GB                   | 4-bit | 100.5 tok/s    | reported | ttft 184ms | vram - GB | ctx 2,048
  AMD Ryzen 7 7840HS                 | 4-bit | 22.3 tok/s     | reported | ttft -ms | vram - GB | ctx 512
  RX 570 4GB                         | 4-bit | 42 tok/s       | reported | ttft 28,364ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 54.9 tok/s     | measured | ttft 78ms | vram - GB | ctx 2,048