bestmodel.run / model — Huihui-Qwen3.8-27B-abliterated-NVFP4 (agent view)

category chat · sakamakismile/Huihui-Qwen3.8-27B-abliterated-NVFP4 · 16 runs in the model record
answer: 135.6 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 5090 32GB                      | 4-bit | 135.6 tok/s    | measured | ttft 931ms | vram - GB | ctx 172,800