bestmodel.run / model — Kimi-Linear-48B-A3B-Instruct (agent view)

category chat · moonshotai/Kimi-Linear-48B-A3B-Instruct · 6 runs in the model record
answer: 233.1 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 PRO 6000 Blackwell 96GB        | 5-bit | 267 tok/s      | reported | ttft 75ms | vram - GB | ctx 262,144
  RTX PRO 6000 Blackwell 96GB        | 6-bit | 256.3 tok/s    | reported | ttft 107ms | vram - GB | ctx 262,144
  RTX PRO 6000 Blackwell 96GB        | 8-bit | 119 tok/s      | measured | ttft 416,256ms | vram - GB | ctx 1,000,000