bestmodel.run / model — Agents-A1-4B-Q4_K_M-GGUF (agent view)

category chat · InternScience/Agents-A1-4B-Q4_K_M-GGUF · 14 runs in the model record
answer: 72.3 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
  RTX 3060 12GB                      | 4-bit | 76.6 tok/s     | measured | ttft 1,132ms | vram - GB | ctx 131,072
  RX 570 4GB                         | 4-bit | 21.4 tok/s     | measured | ttft 93,597ms | vram - GB | ctx 2,048
  RX 7700 XT 12GB                    | 4-bit | 77.7 tok/s     | reported | ttft 99ms | vram - GB | ctx 2,048