logo
welcome
Live Science

Live Science

Large language models can be squeezed onto your phone — rather than needing 1000s of servers to run — after breakthrough

Live Science
Summary
Nutrition label

80% Informative

A new algorithm could compress AI models so they fit onto a smartphone or laptop.

The new algorithm, Calibration Aware Low precision Decomposition with Low Rank Adaptation ( CALDERA ) compresses the massive amounts of data needed to run a large language model (LLM) The results could pave the way for LLMs to be stored and run on smartphones or laptops in the future.