LFM2.5-230M: hardware requirements

LFM2.5-230M needs about 808 MB of memory at Q4 quantization — a 153 MB download plus room for context and overhead. That fits a machine with 8GB RAM.

Parameters
230M
Tier
Runs on a laptop
Licence
See model card
Released
2026-06-26

Will it run on your machine?

Download sizes by quantization

Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?

QuantDownloadRAM @ 4KRAM @ 32KSource
Q4_K_Mrecommended153 MB808 MB1.6 GBmeasured
Q5_K_M172 MB826 MB1.6 GBmeasured
Q6_K191 MB845 MB1.7 GBmeasured
Q8_0247 MB901 MB1.7 GBmeasured
BF16462 MB1.1 GB1.9 GBmeasured

“Measured” sizes are read from published GGUF files (LiquidAI/LFM2.5-230M-GGUF). “Estimated” sizes are derived from the parameter count and are typically within a few percent. The RAM columns add the context cache and runtime overhead to the download size.