apfel: Unlocking Apple's On-Device Language Model on macOS
By
Arthur-Ficial
Summary
Apple ships an on-device language model as part of Apple Intelligence starting with macOS 26 (Tahoe), accessible through the FoundationModels framework. However, Apple only uses it for Siri, Writing Tools, and system features. The article introduces "apfel" — a tool that unlocks this on-device LLM with a single `brew install`, giving developers and users access to local AI inference without network calls, API keys, or cloud dependencies. All inference runs on the Neural Engine and GPU.
Source
bskyapfel: Unlocking Apple's On-Device Language Model on macOSapfel.franzai.comKey quotes
· 4 pulledApple ships an on-device LLM. Starting with macOS 26 (Tahoe), every Apple Silicon Mac includes a language model as part of Apple Intelligence.
All inference runs on the Neural Engine and GPU. No network calls, no cloud, no API keys. The model is just there.
But Apple only uses it for Siri. Out of the box, the on-device model powers Siri, Writing Tools, and system features.
Your Mac already has AI. Apple ships a language model with macOS — apfel unlocks it with one brew install. No downloads, no API keys, no config. The fastest path to local AI.
You might also wanna read
Apple Introduces Multilingual Foundation Language Models for Apple Intelligence Features
Apple introduces two multilingual, multimodal foundation language models for Apple Intelligence features, including an on-device model optim
machinelearning.apple.com·11mo ago
macOS 27 Golden Gate New Features: Design, Siri AI, and Release Dates
Apple reportedly planning third-party AI model support in iOS 27
Apple is reportedly planning to allow users to choose third-party AI models to power Apple Intelligence features in iOS 27, iPadOS 27, and m
The Verge·2mo ago
Running local AI models on an M4 MacBook with 24GB memory: A practical guide
The article details the author's experiments with running local AI language models on an M4 MacBook with 24GB memory. It covers the setup pr
Johanna Larsson·1mo ago
Optimizing LLM Inference by Combining NVIDIA DGX Spark and Apple Mac Studio Architectures
The article explores combining NVIDIA DGX Spark AI supercomputers with Apple Mac Studio systems to optimize large language model (LLM) infer
CoreML-CLI: Command-Line Interface for Apple Core ML Models on macOS
CoreML-CLI is a native command-line interface tool for macOS that enables developers to work with Apple Core ML models directly from the ter
github.com·5mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.