bestmodel.run / model — GLM-5.2-Int4-Int8Mix (agent view)

category chat · QuantTrio/GLM-5.2-Int4-Int8Mix · 66 runs in the model record
answer: 30.6 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 ×10                 | 4-bit | 29.7 tok/s     | measured | ttft 229ms | vram - GB | ctx 131,072
  CMP 170HX 64GB ×8                  | 4-bit | 30.6 tok/s     | measured | ttft 291ms | vram - GB | ctx 131,072