bestmodel.run / model — Huihui-gemma-4-31B-it-abliterated-v2 (agent view)

category chat · huihui-ai/Huihui-gemma-4-31B-it-abliterated-v2 · 1 runs in the model record
answer: 58 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 4090 48GB                      | 6-bit | 58 tok/s       | reported | ttft -ms | vram 31.5 GB | ctx 65,535