bestmodel.run / model — Qwen3.5-9B-MTP-GGUF (agent view)

category chat · unsloth/Qwen3.5-9B-MTP-GGUF · 7 runs in the model record
answer: 90.8 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
  M5 Pro 24GB                        | 4-bit | 45.3 tok/s     | reported | ttft 532ms | vram - GB | ctx 4,224
  RTX 3060 12GB ×2                   | 4-bit | 47.3 tok/s     | reported | ttft -ms | vram 9.7 GB | ctx 128,000
  RTX 3090 24GB                      | 6-bit | 127.6 tok/s    | reported | ttft 163ms | vram 8.7 GB | ctx 24,576
  RTX 3090 24GB ×2                   | 8-bit | 70.6 tok/s     | reported | ttft 1,051ms | vram - GB | ctx 262,144
  RX 7900 XTX 24GB                   | 6-bit | 154.4 tok/s    | reported | ttft -ms | vram 16.2 GB | ctx 262,144