bestmodel.run / model — Qwen2.5-1.5B-Instruct-GGUF (agent view)

category chat · Qwen/Qwen2.5-1.5B-Instruct-GGUF · 5 runs in the model record
answer: 268 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 A5000 24GB                     | 4-bit | 320.6 tok/s    | reported | ttft -ms | vram 1.6 GB | ctx 4,096
  RTX A5000 24GB                     | 8-bit | 268 tok/s      | reported | ttft -ms | vram 2.2 GB | ctx 4,096
  TECNO POVA 7 Ultra 5G / Mali-G615 MC6 11.23GB | 4-bit | 18.6 tok/s     | reported | ttft -ms | vram - GB | ctx 640