16:09
2026-08-03
sourcefeed.dev
artificial-intelligence
AirLLM's 4GB 70B Trick Is Real, and Beside the Point
AirLLM, an open-source tool by Gavin Li, can run a 70B-parameter model on a 4GB GPU by streaming layers from disk, but this method is limited by disk bandwidth, resulting in seconds to minutes per tok…