bestmodel.run / model — Qwen3-Coder-30B-A3B-Instruct-GGUF (agent view)

category code · unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · 10 runs in the model record
answer: 70.4 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
  Arc Pro B70 32GB                   | 4-bit | 108.1 tok/s    | reported | ttft 164ms | vram - GB | ctx 4,096
  Radeon 890M 32GB                   | 4-bit | 30 tok/s       | reported | ttft 1,500ms | vram - GB | ctx 2,048
  Ryzen AI Max 385 24GB              | 4-bit | 30 tok/s       | reported | ttft 1,500ms | vram - GB | ctx 2,048
  Ryzen AI Max 395 128GB             | 4-bit | 70.3 tok/s     | measured | ttft 191ms | vram 18.8 GB | ctx 65,536
  Ryzen AI Max 395 64GB              | 4-bit | 88.9 tok/s     | measured | ttft 791ms | vram 18.3 GB | ctx 8,192