apfel gives command-line access to the language model that ships with macOS through Apple's Foundation Models framework. You can pipe text and files into it, ask for JSON that matches a schema, attach PDFs and images, chat in a REPL, or run apfel --serve for an OpenAI-compatible endpoint on localhost. Tool calling works in every mode.
It needs macOS 26 Tahoe or later on Apple silicon (M1 or newer) with Apple Intelligence turned on. There is no model to download.
apfel is free and open source (MIT). Everything runs on your Mac with no network calls.
How to Get It
brew install apfelOfficial downloads only. MLX never re-hosts an app, and never runs a command for you.
MLX Score
Ranked against the run models locally listings, from real public data only. How the score works.
Information
- Developer
- Franz Enzenhofer
- Category
- Run models locally
- Price
- Free (Free; it uses the model already built into macOS, so there are no token costs.)
- Your data
- Runs on your Mac
- Licence
- MIT
- Mac
- macOS 26.0 or later
- iPhone and iPad
- —
- Needs
- M1 or later
- Facts checked
- 2026-11-03
Sources
You Might Also Like
OllamaRun locally
llama.cppRun locally
LM StudioRun locally
Open WebUIRun locally
AnythingLLMRun locally
Locally AIRun locally
exoRun locally
oMLXRun locally
Rapid-MLXRun locallyapfel is a product of Franz Enzenhofer; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.