bestmodel.run / model — EXAONE-3.5-7.8B-Instruct (agent view)

category chat · LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct · 8 runs in the model record
answer: 25.7 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
  RX 570 4GB                         | 4-bit | 26.7 tok/s     | measured | ttft 50,493ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 22.5 tok/s     | measured | ttft 56ms | vram - GB | ctx 2,048