A curated collection of machine learning models in Core ML format for iOS, macOS, tvOS, and watchOS developers.
Awesome Core ML Models is a curated repository of machine learning models converted to Apple's Core ML format. It provides iOS, macOS, tvOS, and watchOS developers with a collection of pre-trained models for tasks like image recognition, text analysis, and speech processing, enabling quick integration of ML features into apps.
Apple platform developers (iOS, macOS, tvOS, watchOS) who want to add machine learning capabilities to their applications without training models from scratch.
It offers the largest collection of ready-to-use Core ML models with demo projects, saving developers time on model conversion and providing practical implementation examples.
Largest list of models for Core ML (for iOS 11+)
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
It's explicitly billed as the largest curated list of Core ML models, spanning image recognition, text processing, speech, and more—saving developers from scouring multiple sources.
All models are already in Core ML (.mlmodel) format, ready for direct Xcode integration, eliminating the need for manual conversion using tools like coremltools.
Each model entry links to sample applications (e.g., PoseEstimation-CoreML demo), providing practical, copy-pasteable Swift code for faster implementation.
Models work across iOS, macOS, tvOS, and watchOS, leveraging Apple's unified Core ML framework for broad ecosystem support.
As a community-driven list, it may not include cutting-edge models promptly; for instance, newer architectures like Vision Transformers are absent, relying on pull requests for updates.
Listings provide only basic download/demo links without performance metrics, size constraints, or accuracy benchmarks—forcing developers to test blindly or seek external docs.
Demo and reference URLs (e.g., Google Drive links) can become outdated or invalid over time, as seen with some older entries, complicating dependency management.