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

category chat · openbmb/MiniCPM5-1B-GGUF · 37 runs in the model record
answer: 99.8 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
  RTX 3060 12GB ×2                   | 4-bit | 125.9 tok/s    | reported | ttft -ms | vram 4.3 GB | ctx 128,000
  RX 570 4GB                         | 4-bit | 106 tok/s      | measured | ttft 49ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 70 tok/s       | measured | ttft 47ms | vram - GB | ctx 2,048
  RX 5700 8GB                        | 4-bit | 221.6 tok/s    | reported | ttft 16ms | vram - GB | ctx 2,048