‹ BackHN Continuity

Thread

macOS 27: Workaround to avoid downloading AI models and save storage

240 points · 123 comments · ano-ther

  1. jtbayly · · focus · HN ↗
    Yeah, I’ll wait to update my computers until Apple gives us an actual choice.
    1. sleepybrett · · focus · HN ↗
      why is a local model any different than any other file they want to install with their os?
      1. alwillis · · focus · HN ↗
        Friendly reminder:

        Many apps (like dictation apps) ship with their own models totally separate from Apple Intelligence.

        For example, Co-Typist [1] is very useful, but it requires a model installed with it, ranging from Gemma 3 1B at 0.8 GB to Gemma 4 26B A4B Pro at 15.7 GB. It recommended Gemma E2B (3.2 GB) for my 16 GB, M1 Pro MacBook Pro.

        It works really well; the autocompletion is so good, it knows what I'm going to type before I do!

        Here's the thing: you may not be aware of the amount of storage being used by models in various 3rd-party apps.

        The open-source app What The Model [2] scans your machine and reports all the models it finds and gives you the total amount of storage being used.

        [1]: <a href="https:&#x2F;&#x2F;cotypist.app" rel="nofollow">https:&#x2F;&#x2F;cotypist.app

        [2]: <a href="https:&#x2F;&#x2F;github.com&#x2F;powtac&#x2F;wtm" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;powtac&#x2F;wtm

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.