bestmodel.run / model — Qwen3.8-27B-MTP-GGUF (agent view)

category chat · Jackrong/Qwen3.8-27B-MTP-GGUF · 235 runs in the model record
answer: 36.6 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
  CMP 170HX 64GB                     | 4-bit | 42 tok/s       | measured | ttft 24,545ms | vram - GB | ctx 131,296
  CMP 170HX 64GB                     | 8-bit | 32.7 tok/s     | measured | ttft 22,198ms | vram - GB | ctx 132,352