Liquid AI releases LFM2.5-230M, beats 4x larger models

VentureBeat

Liquid AI released LFM2.5-230M, a 230-million-parameter model that outperforms models 4x its size on data extraction tasks. The model is built for on-device deployment on smartphones, laptops, and robotics, with a community demo showing in-browser inference at 1,400 tok/s using custom WebGPU kernels.

See 1 more source

LFM2.5 230M running in-browser at 1,400 tok/s using custom WebGPU kernels7 hours agoxenovatechDiscuss

VentureBeat·Carl Franzen

5 hours ago