Apple Reportedly Developing App for Running Local AI Models

Nov. 11: According to Gelonghui, a leaker has disclosed that Apple is developing a Mac app called Harbor that can turn Apple-silicon computers into private AI inference servers, supporting direct download, management and running of open-weight models, with no need to upload data to the cloud. The app can also connect two or more compatible Macs via Thunderbolt 5, automatically forming a cluster and pooling unified memory to run large models that exceed a single machine's capacity or to handle more concurrent requests, without manual configuration or use of the command line. The app is currently in private preview at Claris, Apple's software subsidiary, and no official launch date has been announced.