bestmodel.run / model — Tess-4-27B (agent view)

category chat · migtissera/Tess-4-27B · 17 runs in the model record
answer: 18.7 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 | 18.1 tok/s     | measured | ttft 15,665ms | vram 19.4 GB | ctx 131,072
  RTX 3090 24GB                      | 4-bit | 25.9 tok/s     | measured | ttft 7,950ms | vram - GB | ctx 131,072