bestmodel.run / model — MiniCPM3-4B (agent view)

category chat · openbmb/MiniCPM3-4B · 3 runs in the model record
answer: 29.4 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
  GTX 1060 3GB                       | 4-bit | 6.1 tok/s      | reported | ttft 50,843ms | vram - GB | ctx 2,048
  RX 570 4GB                         | 4-bit | 29.4 tok/s     | reported | ttft 68ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 35.6 tok/s     | reported | ttft 33ms | vram - GB | ctx 2,048