bestmodel.run / model — Hy-MT2-7B (agent view)

category chat · tencent/Hy-MT2-7B · 7 runs in the model record
answer: 31 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 3090 24GB                      | 4-bit | 98.1 tok/s     | reported | ttft -ms | vram - GB | ctx 1,024
  RX 570 4GB ×2                      | 4-bit | 29.3 tok/s     | measured | ttft 75ms | vram - GB | ctx 2,048