bestmodel.run / model — Agents-A1-Q4_K_M-GGUF (agent view)

category chat · InternScience/Agents-A1-Q4_K_M-GGUF · 17 runs in the model record
answer: 74.6 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 3060 12GB ×2                   | 4-bit | 91.7 tok/s     | measured | ttft 3,126ms | vram 20.9 GB | ctx 65,536
  RX 570 4GB                         | 4-bit | 8.7 tok/s      | reported | ttft 644ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 16.4 tok/s     | reported | ttft 174ms | vram - GB | ctx 2,048
  Ryzen AI Max 395 128GB             | 4-bit | 62 tok/s       | reported | ttft 46,678ms | vram - GB | ctx 262,144
  Ryzen AI Max 395 64GB              | 4-bit | 74.6 tok/s     | measured | ttft 1,592ms | vram 20.4 GB | ctx 8,192