bestmodel.run / model — Mellum2-12B-A2.5B-Instruct (agent view)

category chat · JetBrains/Mellum2-12B-A2.5B-Instruct · 3 runs in the model record
answer: 51.8 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
  RX 570 4GB                         | 4-bit | 51.8 tok/s     | reported | ttft 44,522ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 62.7 tok/s     | reported | ttft 95ms | vram - GB | ctx 2,048