bestmodel.run / model — LFM2.5-8B-A1B-GGUF (agent view)

category chat · LiquidAI/LFM2.5-8B-A1B-GGUF · 18 runs in the model record
answer: 218.2 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
  AMD Ryzen 5 7640U                  | 4-bit | 22.3 tok/s     | reported | ttft 577ms | vram - GB | ctx 2,048
  RTX 3060 12GB ×2                   | 4-bit | 218.2 tok/s    | measured | ttft -ms | vram 6.4 GB | ctx 128,000
  RTX 3060 12GB ×2                   | 6-bit | 175.6 tok/s    | reported | ttft -ms | vram 8.2 GB | ctx 128,000
  RTX 3080 12GB                      | 4-bit | 328.4 tok/s    | reported | ttft 261ms | vram 6.4 GB | ctx 128,000
  RTX 3080 12GB                      | 6-bit | 277.8 tok/s    | reported | ttft 286ms | vram 8.1 GB | ctx 128,000
  RTX 3090 24GB ×2                   | 8-bit | 276.3 tok/s    | measured | ttft 317ms | vram - GB | ctx 128,000
  RX 570 4GB ×2                      | 4-bit | 160.7 tok/s    | measured | ttft 1,630ms | vram - GB | ctx 2,048