Evidence of a new Apple Mac application called Harbor has been discovered by leaker Aaron Perris. This app is designed to facilitate the local execution of AI models on Mac computers, transforming them into private AI inference servers.
Harbor allows users to run open-weight AI models directly on Apple silicon, ensuring that data remains on the user's hardware and does not interact with cloud services. The app handles model management, enabling users to browse, download, and load models from within the application interface.
A key feature of Harbor is its ability to cluster multiple Thunderbolt 5-capable Mac computers. By connecting these devices, Harbor pools their unified memory into a single resource. This allows for the execution of AI models that exceed the capacity of a single Mac or to serve more concurrent requests across the cluster.
The application is designed for ease of use, with setup described as taking minutes. Harbor automatically detects devices over Thunderbolt 5 to form a cluster, eliminating the need for manual configuration, command-line operations, or infrastructure expertise.
Harbor is currently in a private preview phase under Apple's Claris brand. A public launch is anticipated in the coming weeks or months, indicating Apple's increased focus on local AI processing capabilities for its Mac lineup.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Apple is developing a new Mac application named Harbor, which allows users to run open-weight AI models locally on Apple silicon devices. The app can pool unified memory across multiple Thunderbolt 5-connected Macs to handle larger models and higher concurrency, positioning Macs as private AI inference servers.