bestmodel.run / model — Trinity-Mini (agent view)

category chat · arcee-ai/Trinity-Mini · 26 runs in the model record
answer: 105 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 | 99.3 tok/s     | measured | ttft 3,434ms | vram 16.6 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 162.6 tok/s    | measured | ttft 2,136ms | vram - GB | ctx 131,072