bestmodel.run / model — Qwen3.6-35B-A3B-MTP-GGUF (agent view)

category chat · unsloth/Qwen3.6-35B-A3B-MTP-GGUF · 39 runs in the model record
answer: 72.8 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
  Arc B580 12GB                      | 5-bit | 19.6 tok/s     | reported | ttft -ms | vram 11.4 GB | ctx 262,144
  GTX 1080 Ti 11GB                   | 4-bit | 39.4 tok/s     | reported | ttft -ms | vram 10 GB | ctx 128,000
  M5 Max 128GB                       | 4-bit | 97 tok/s       | measured | ttft 99ms | vram - GB | ctx 2,048
  M5 Pro 24GB                        | 3-bit | 80.4 tok/s     | reported | ttft 54ms | vram - GB | ctx 65,536
  Radeon AI Pro R9700 32GB           | 4-bit | 56.7 tok/s     | reported | ttft 0ms | vram 24.5 GB | ctx 2,048
  RTX 3060 12GB                      | 2-bit | 39.2 tok/s     | measured | ttft 3,477ms | vram - GB | ctx 2,048
  RTX 3060 12GB                      | 4-bit | 24.6 tok/s     | reported | ttft 3,009ms | vram - GB | ctx 8,320
  RTX 3060 12GB ×2                   | 4-bit | 98.9 tok/s     | reported | ttft 86ms | vram - GB | ctx 2,048
  RTX 3090 24GB                      | 3-bit | 195.1 tok/s    | reported | ttft 24ms | vram 20.2 GB | ctx 163,840
  RTX 3090 24GB                      | 4-bit | 121.6 tok/s    | reported | ttft 87ms | vram 23.2 GB | ctx 262,144
  RTX 4090 24GB                      | 4-bit | 213.9 tok/s    | reported | ttft -ms | vram - GB | ctx 32,768
  RTX 5060 Ti 16GB                   | 3-bit | 119.1 tok/s    | reported | ttft -ms | vram - GB | ctx 150,000
  RTX 5060 Ti 16GB                   | 4-bit | 36.7 tok/s     | reported | ttft -ms | vram 16 GB | ctx 131,072
  RTX 5060 Ti 16GB ×2                | 4-bit | 129.1 tok/s    | reported | ttft 93ms | vram - GB | ctx 8,192
  RTX 5070 12GB                      | 4-bit | 64.5 tok/s     | reported | ttft 228ms | vram - GB | ctx 64,000
  RTX 5070 Ti 16GB ×2                | 4-bit | 141 tok/s      | reported | ttft 123ms | vram 29,335 GB | ctx 163,840
  RTX 5090 32GB                      | 4-bit | 222.9 tok/s    | reported | ttft 89ms | vram 28.6 GB | ctx 65,536
  RTX 5090 32GB                      | 5-bit | 265.4 tok/s    | reported | ttft 57ms | vram - GB | ctx 2,048
  RX 6700 10GB                       | 3-bit | 10.1 tok/s     | reported | ttft 2,781ms | vram 4 GB | ctx 4,096
  RX 7900 XTX 24GB ×2                | 4-bit | 109.5 tok/s    | reported | ttft 183ms | vram - GB | ctx 2,048
  Ryzen AI Max 395 128GB             | 4-bit | 54.5 tok/s     | measured | ttft 32,830ms | vram 24.4 GB | ctx 262,144
  Ryzen AI Max 395 64GB              | 4-bit | 60.5 tok/s     | measured | ttft 1,575ms | vram 21.5 GB | ctx 8,192