Command-line tool quickly removes Apple Intelligence from macOS 27
Ars Technica
5 Oct 2026, 19:14 UTC
·
1 min read
In brief
A GitHub developer known as Om Lahore has released RemoveMacAI, a command-line utility for disabling Apple Intelligence on macOS 27 Golden Gate. The tool is described as fully reversible and can remove the locally stored AI models, which remain installed despite the system lacking a global disable switch.
macOS 27 Golden Gate does not provide a single setting to turn off Apple Intelligence.
RemoveMacAI is intended to disable the feature and remove its models from the Mac.
Apple says the models use about 12GB; The Verge reported that they can occupy more than 30GB.
The utility is available as a command-line tool on GitHub.
Why it matters: The release gives users more control over system storage and AI features on macOS 27.
Editorial brief by Sakhanda Wire AI, based on reporting by Ars Technica.
A new tool is allowing Mac users the ability again to easily turn off Apple Intelligence with one click and free up to 12GB of storage.
Unlike with previous versions of macOS, macOS 27 Golden Gate doesn’t have a toggle for turning off Apple Intelligence. That makes disabling AI features that you may not want more difficult. It also means that the AI models necessary for running Apple Intelligence will take up space on your disk, even if you don’t use them or if you go through your settings to individually find and disable AI capabilities.
In response, a developer known as Om Lahore on GitHub last week created RemoveMacAI, a command-line tool that allows macOS 27 users to “turn off Apple Intelligence on macOS 27" in a way that is “fully reversible,” per the GitHub page . They said that Apple's Intelligence models take up "about 12GB," but the models can actually take up over 30GB, The Verge noted.
Read full article
Comments
Originally published by Ars Technica on 5 Oct 2026, 19:14 UTC
Read the original on Ars Technica ↗
Text and images are the property of Ars Technica and are reproduced here with attribution and a link to the original publication.
