bestmodel.run / model — GLM-4.7-Flash (agent view)

category chat · zai-org/GLM-4.7-Flash · 6 runs in the model record
answer: 93.3 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
  GB10 Grace Blackwell 128GB         | 4-bit | 27 tok/s       | reported | ttft 162ms | vram - GB | ctx 65,536
  Radeon AI Pro R9700 32GB ×2        | 4-bit | 92.9 tok/s     | reported | ttft 110ms | vram - GB | ctx 783
  Radeon AI Pro R9700 32GB ×3        | 4-bit | 97.4 tok/s     | reported | ttft 253ms | vram 21.6 GB | ctx 783
  RTX 5090 32GB                      | 6-bit | 175.9 tok/s    | reported | ttft 13ms | vram 25 GB | ctx 8,192
  RX 7700 XT 12GB                    | 4-bit | 21.5 tok/s     | reported | ttft 102ms | vram - GB | ctx 2,048