bestmodel.run / model — Qwen3-VL-8B-Instruct-GGUF (agent view)

category chat · unsloth/Qwen3-VL-8B-Instruct-GGUF · 2 runs in the model record
answer: 14.1 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
  Radeon 890M 32GB                   | 4-bit | 14.1 tok/s     | reported | ttft 1,600ms | vram - GB | ctx 2,048
  Ryzen AI Max 385 24GB              | 4-bit | 14.1 tok/s     | reported | ttft 1,600ms | vram - GB | ctx 2,048