bestmodel.run / model — GLM-5.2-Alis-MLX-Dynamic-2.3bpw (agent view)

category chat · avlp12/GLM-5.2-Alis-MLX-Dynamic-2.3bpw · 1 runs in the model record
answer: 19.8 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
  M3 Ultra 512GB                     | 2-bit | 19.8 tok/s     | reported | ttft -ms | vram 222.9 GB | ctx 2,048