bestmodel.run / model — LFM2.5-1.2B-Instruct-GGUF (agent view)

category chat · LiquidAI/LFM2.5-1.2B-Instruct-GGUF · 31 runs in the model record
answer: 120.3 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
  M5 Pro 24GB                        | 4-bit | 267.8 tok/s    | reported | ttft 90ms | vram - GB | ctx 4,224
  RTX 3090 24GB                      | 4-bit | 682.2 tok/s    | measured | ttft 25ms | vram 2.4 GB | ctx 24,576
  RTX 3090 24GB                      | 6-bit | 564.4 tok/s    | measured | ttft 28ms | vram 2.6 GB | ctx 24,576
  RX 570 4GB                         | 4-bit | 118 tok/s      | measured | ttft 26ms | vram - GB | ctx 2,048
  RX 570 4GB ×2                      | 4-bit | 120.6 tok/s    | measured | ttft 22ms | vram - GB | ctx 2,048