bestmodel.run / model — MiniCPM5-1B (agent view)

category chat · openbmb/MiniCPM5-1B · 16 runs in the model record
answer: 101.3 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
  RX 570 4GB                         | 4-bit | 117.6 tok/s    | measured | ttft 18ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 97.8 tok/s     | measured | ttft 25ms | vram - GB | ctx 2,048