bestmodel.run / model — Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced (agent view)

category chat · HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced · 2 runs in the model record
answer: 31.6 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                      | 4-bit | 38.4 tok/s     | reported | ttft 3,331ms | vram 9.9 GB | ctx 4,608
  Ryzen AI Max 395 128GB             | 4-bit | 24.8 tok/s     | reported | ttft 216ms | vram 9.7 GB | ctx 4,096