bestmodel.run / model — Qwen3.5-35B-A3B-GGUF (agent view)

category chat · unsloth/Qwen3.5-35B-A3B-GGUF · 17 runs in the model record
answer: 72.9 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
  BC-250 8GB                         | 2-bit | 73.2 tok/s     | measured | ttft 9,290ms | vram - GB | ctx 12,552
  GB10 Grace Blackwell 128GB         | 4-bit | 60.3 tok/s     | reported | ttft -ms | vram - GB | ctx 262,144
  GB10 Grace Blackwell 128GB         | 8-bit | 35.1 tok/s     | reported | ttft -ms | vram - GB | ctx 262,144
  Minisforum UM790 Pro 64GB          | 4-bit | 23.6 tok/s     | reported | ttft -ms | vram - GB | ctx 2,048
  RTX 3090 24GB                      | 4-bit | 124.4 tok/s    | reported | ttft -ms | vram - GB | ctx 2,048
  RTX 4090 24GB                      | 4-bit | 157.4 tok/s    | reported | ttft -ms | vram - GB | ctx 2,048