bestmodel.run / model — reka-flash-3 (agent view)

category chat · RekaAI/reka-flash-3 · 23 runs in the model record
answer: 23.1 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 3060 12GB ×2                   | 4-bit | 22.3 tok/s     | measured | ttft 4,802ms | vram 18.5 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 32.3 tok/s     | measured | ttft 3,950ms | vram - GB | ctx 131,072