Skip to main content

AI models that run on this device.

Two small chat models run in a computer’s browser here; every other model is a file you download.

Run local AI on a Mac

LEARN / LOCAL AI Sources checked

Apple silicon Macs can use the Hugging Bay app, Ollama or LM Studio; Intel Macs can use Ollama on a supported macOS version.

1. Check your Mac

Open Apple menu → About This Mac. Note Chip or Processor, Memory and macOS version. Use the memory guide before choosing a model.

2. Install the Hugging Bay app on Apple silicon

The live download page checked on 17 October 2026 lists Apple silicon and macOS 11 or later. Open our download page, download the Mac disk image, and compare its SHA-256 using the command on that page.

Open the disk image, put the app in Applications, and launch it. Follow the machine check. Continue with the first-chat steps. If macOS blocks an unrecognized or damaged copy, download it again from that page; do not disable Gatekeeper.

3. Or use Ollama or LM Studio

Ollama requires macOS 14 or later. Download it from Ollama, open its disk image, drag it to Applications, and launch it. Complete its command-line setup, then open Terminal and follow the Ollama chat steps. Intel Macs use CPU processing.

For a point-and-click alternative, LM Studio requires Apple silicon and macOS 14 or later. Install the Mac app and follow the LM Studio steps. LM Studio does not currently support Intel Macs.

Prefer the terminal?

The native hbay guide covers macOS and Linux. Its installer requires OpenSSL 3 or newer; the system LibreSSL on a Mac does not meet that requirement.

Sources and checks

Checked 2026-10-17. Install requirements and availability can change; the linked source has current details.

Read as Markdown