Apple reportedly tests Harbor for local AI inference on Macs
9to5Mac, citing leaker Aaron Perris, reported that Apple is developing a Mac app called Harbor to run open-weight models locally and potentially serve private AI inference. Product materials described in the reports say Harbor can manage models and cluster multiple Thunderbolt 5 Macs by pooling unified memory, although these capabilities have not been independently tested. IT之家 and other outlets reported that Claris is testing the app in an early-access program and that its App Store listing was briefly removed, leaving public availability unsettled.
Harbor could position Apple silicon Macs as an integrated platform for private, multi-device AI inference rather than leaving deployment primarily to third-party tools such as LM Studio and Ollama.

Leaker Aaron Perris has discovered evidence of a new Mac app in the works at Apple called Harbor, which makes it easy to run local AI models across one or more Macs.
New ‘Harbor’ app revealed at Apple: ‘turns your Mac into a private AI inference server’

The Mac has been getting a lot more popular this year, both because of budget-friendly options like MacBook Neo but also as a tool for running AI models locally on Mac Studio, Mac mini, and more.
It seems Apple plans to lean harder into the latter use case, as leaker Aaron Perris has discovered a new Mac app called Harbor that’s been designed to turn your Mac into a private AI inference server.
#Apple#Claris#Harbor#Apple silicon#macOS Tahoe 26.2#Thunderbolt 5#LM Studio#Ollama