john-rocky/CoreML-Models

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.

What it solves

Integrating high-performance AI models into iOS and Android applications often requires complex conversion processes. This project provides a curated collection of pre-converted Core ML models and sample apps, allowing developers to easily implement on-device AI without having to convert the models themselves.

How it works

The repository acts as a model zoo where developers can browse a catalog of models across various AI domains. Users download the desired model (typically in .mlpackage or .aimodel format) via provided Google Drive or release links and bundle them directly into their Xcode projects. For many models, the repository also provides sample projects to demonstrate implementation.

Who it’s for

Mobile app developers targeting Apple's ecosystem (iOS/macOS) who want to add machine learning capabilities to their apps using Core ML.

Highlights

  • Extensive Model Variety: Includes models for image classification, object detection (YOLO series), segmentation (SAM2, MobileSAM), super-resolution, and image generation.
  • Multimodal Support: Provides converted models for text-to-speech, voice conversion, and vision-language tasks (Florence-2).
  • LLM Integration: Includes Core ML versions of language models like Gemma 4 and Qwen3.5.
  • Ready-to-Use: Offers sample apps and conversion scripts (via Colab) for several models to accelerate development.

Related

  • Project
    john-rocky/coreai-model-zoo

    A collection of converted AI models and conversion recipes for Apple Core AI, enabling easy on-device deployment of LLMs, VLMs, and other frontier models on iOS and macOS.

  • Project
    qualcomm/ai-hub-models

    A collection of state-of-the-art ML models optimized for Qualcomm devices, featuring tools to compile, quantize, and profile models for on-device deployment.

  • Project
    ultralytics/yolo-ios-app

    A Swift-based SDK and demo app that brings real-time YOLO object detection and vision tasks to iOS devices using Core ML.

  • Project
    apple/coremltools

    A Python package for converting machine learning models from frameworks like PyTorch and TensorFlow into the Core ML format for on-device deployment on Apple devices.

  • Project
    PINTO0309/PINTO_model_zoo

    A comprehensive collection of AI models pre-converted and quantized across various frameworks like TensorFlow, PyTorch, ONNX, and CoreML for easier deployment on edge devices.