bestmodel.run / model — GLM-5.2-MXFP8-NVFP4-NF3-Hybrid (agent view)

category chat · madeby561/GLM-5.2-MXFP8-NVFP4-NF3-Hybrid · 4 runs in the model record
answer: 74.4 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 PRO 6000 Blackwell 96GB ×4     | 4-bit | 74.4 tok/s     | reported | ttft 175ms | vram - GB | ctx 480,000
  RTX PRO 6000 Blackwell 96GB ×4     | 8-bit | 68.4 tok/s     | reported | ttft 283ms | vram - GB | ctx 480,000