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

category chat · unsloth/GLM-4.7-Flash-GGUF · 9 runs in the model record
answer: 66 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
  Arc Pro B70 32GB                   | 4-bit | 40.8 tok/s     | reported | ttft 206ms | vram - GB | ctx 4,096
  Radeon AI Pro R9700 32GB           | 2-bit | 82.1 tok/s     | reported | ttft 250ms | vram - GB | ctx 2,048
  Radeon AI Pro R9700 32GB           | 4-bit | 75.8 tok/s     | reported | ttft 196ms | vram - GB | ctx 2,048
  Ryzen AI Max 395 128GB             | 4-bit | 52.8 tok/s     | reported | ttft 211ms | vram 17.6 GB | ctx 4,096
  Ryzen AI Max 395 64GB              | 4-bit | 65.7 tok/s     | measured | ttft 1,175ms | vram 17.3 GB | ctx 8,192