bestmodel.run / model — Step-3.7-Flash-GGUF (agent view)

category chat · stepfun-ai/Step-3.7-Flash-GGUF · 9 runs in the model record
answer: 30.7 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                | 4-bit | 20.8 tok/s     | reported | ttft -ms | vram 95.6 GB | ctx 32,768
  GB10 Grace Blackwell 128GB         | 4-bit | 23 tok/s       | reported | ttft 8,470ms | vram - GB | ctx 2,048
  RTX 3090 24GB ×8                   | 4-bit | 52.7 tok/s     | reported | ttft 199ms | vram - GB | ctx 262,144
  Ryzen AI Max 395 128GB             | 4-bit | 22 tok/s       | reported | ttft 36,084ms | vram - GB | ctx 65,536
  Ryzen AI Max 395 64GB              | 1-bit | 30.8 tok/s     | measured | ttft 3,334ms | vram 53.8 GB | ctx 4,096