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

category chat · unsloth/LFM2-8B-A1B-GGUF · 8 runs in the model record
answer: 231.4 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 ×2                   | 4-bit | 231.4 tok/s    | measured | ttft 900ms | vram 6.4 GB | ctx 131,072