bestmodel.run / model — Qwen3.5-0.8B-GGUF (agent view)

category chat · unsloth/Qwen3.5-0.8B-GGUF · 4 runs in the model record
answer: 143.8 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
  RTX 3060 12GB                      | 16-bit | 143.3 tok/s    | reported | ttft 590ms | vram 3.3 GB | ctx 4,608
  Tesla P100 32GB ×2                 | 4-bit | 209.4 tok/s    | reported | ttft 109ms | vram 1.3 GB | ctx 2,048
  Tesla P100-PCIE-16GB 16GB          | 5-bit | 136.5 tok/s    | reported | ttft -ms | vram - GB | ctx 2,048
  Tesla P100-PCIE-16GB 16GB ×2       | 5-bit | 144.3 tok/s    | reported | ttft -ms | vram - GB | ctx 2,048