bestmodel.run / model — GLM-5.3-Flash-AWQ-W4A16 (agent view)

category chat · wtdcode/GLM-5.3-Flash-AWQ-W4A16 · 1 runs in the model record
answer: 75.2 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 3090 24GB ×8                   | 4-bit | 75.2 tok/s     | reported | ttft 358ms | vram 183.4 GB | ctx 204,800