core-ai

Core ML model zoo for iOS/macOS — PyTorch models converted to ready-to-use .mlpackage, each with a conversion script and SwiftUI sample app. Sibling repos cover Apple's Core AI framework (iOS/macOS 27) and on-device LLMs.

Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac. Chat, vision, speech and generative models with per-model validation records, Swift examples through CoreAIKit, and a downloadable Mac app.

Swift SDK for running chat, vision and speech models on iPhone and Mac with Apple's Core AI. Model download and caching, FoundationModels integration, and runnable examples with documented OS, SDK and model requirements.

Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the same model and harness, every number with its quantization and capture session; hybrid Mamba-2 models (Nemotron-3 Nano, Granite-4.0-H, Falcon-H1) included.

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.

Complete Really Simple Licensing (RSL) support for WordPress sites. Define machine-readable licensing terms for your content, enabling AI companies, crawlers, and other automated systems to properly license your digital assets.

670 MB/s Swift tokenizer inspired by Marcel Roed’s gigatoken. Zero-copy, NEON/CRC32, WebAssembly, and Embedded Swift.

Use many on device and cloud models with Apple's Foundation Models framework in iOS and macOS with a full chat experience.

Curated resources for Apple's Core AI: official documentation, model downloads, Swift packages, sample apps, benchmarks and practical learning material for on-device AI on iPhone and Mac.

Free hands-on book about bringing AI models to iPhone and Mac with Apple's Core AI. Follow practical explanations and labs from model export to Swift integration and custom Metal kernels. English edition online; Japanese edition on Zenn.

Sample apps for Apple's Core AI framework on Mac. Start with a SwiftUI chat app for exported LLM bundles, then follow the model zoo and CoreAIKit for model downloads and integration examples.

Discover Awesome Core AI Models For Any Project

On-device agentic API demos (Foundation Models) running on third-party Core AI zoo models via coreai-kit

Test, compare, and benchmark language models on macOS and iOS using Apple’s Foundation Models framework.

Model export recipes, Python primitives, and Swift runtime utilities for on-device AI

On-device BLE tracker detector implementing the Apple-Google DULT spec (IETF draft-ledvina-apple-google-unwanted-trackers-02) with Core AI on-device ML inference — built with Swift, Core Bluetooth, and Apple's WWDC 2026 Core AI framework.

Converted CoreML Models and Quantized Variations

Source-grounded registry of Apple Core AI models, artifacts, upstreams, benchmarks, and provenance.

Reproducible Qwen3-1.7B Core AI INT4 GPU conversion, physical-device benchmarks, and W8/ANE comparison.

Pull, convert, quantize, benchmark, serve, and package open-weight LLMs for Apple Silicon (MLX → Core AI)