spb/tools-spboucher-ai

1{2  "slug": "core-ml",3  "name": "Core ML",4  "aliases": ["CoreML", "coremltools"],5  "vendor": { "name": "Apple Inc.", "slug": "apple", "website": "https://developer.apple.com/" },6  "homepage_url": "https://developer.apple.com/documentation/coreml",7  "docs_url": "https://apple.github.io/coremltools/docs-guides/",8  "repo_url": "https://github.com/apple/coremltools",9  "product_type": "framework",10  "product_status": "active",11  "summary": "Apple's on-device machine-learning runtime for iOS and macOS apps, with the open-source coremltools package for converting PyTorch and other models to its format",12  "description": "Core ML is Apple's framework for running machine-learning models inside apps on iPhone, iPad, Mac, Apple Watch, Apple TV and Vision Pro. A model is packaged in the Core ML format (`.mlmodel` or `.mlpackage`), bundled with the app and executed on the device, where the framework schedules work across CPU, GPU and the Neural Engine. It underlies Apple's higher-level Vision, Natural Language, Speech and Sound Analysis frameworks and supports on-device fine-tuning of updatable models.\n\nModels reach Core ML in two ways: Create ML trains common model types directly, and the open-source Python package coremltools (BSD-3-Clause, maintained by Apple on GitHub) converts models from PyTorch, TensorFlow and other libraries, applying quantization, palettization and pruning to reduce size. Xcode shows a model's inputs, outputs and performance report and generates a typed Swift interface.\n\nCore ML is the deployment route for shipping a model in an Apple app; it is not a training framework and is not available outside Apple platforms. Conversion can fail for operators coremltools does not support, and very large language models are constrained by device memory and conversion effort, which is why MLX is often used for research and Core ML for shipping.",13  "capabilities": ["On-device inference across CPU, GPU and Neural Engine", "Model conversion from PyTorch and TensorFlow with coremltools", "Quantization, palettization and pruning for compact models", "Typed Swift interfaces generated by Xcode", "On-device updates of updatable models", "Foundation for Vision, Natural Language and Speech frameworks"],14  "workflows": ["Convert a PyTorch classifier and ship it in an iOS app", "Profile a model's latency per compute unit in Xcode", "Run image analysis offline with Vision on top of Core ML"],15  "advantages": ["Inference stays on the device; no network or server cost", "Hardware scheduling handled by the system", "Open-source conversion tooling"],16  "limitations": ["Apple platforms only", "Not a training framework", "Unsupported operators block conversion", "Large models constrained by device memory"],17  "prerequisites": ["Xcode and an Apple platform target", "Python with coremltools for conversion"],18  "audiences": ["iOS and macOS developers embedding ML", "ML engineers deploying models to Apple devices"],19  "alternatives": ["mlx", "pytorch", "llama-cpp", "apple-foundation-models"],20  "categories": [{ "slug": "apple-silicon-ml", "primary": true }, { "slug": "local-inference" }],21  "tags": ["apple-silicon", "macos", "ios", "on-device-ml", "swift", "python", "model-conversion"],22  "use_cases": ["run-local-models", "serve-models", "build-native-apps"],23  "operating_systems": ["macos", "ios"],24  "execution_modes": ["local"],25  "interfaces": ["sdk", "library"],26  "deployment_models": ["embedded"],27  "integrations": ["Xcode", "Create ML", "Vision", "Natural Language", "PyTorch (via coremltools)", "TensorFlow (via coremltools)"],28  "data_formats": [".mlmodel", ".mlpackage", "ONNX (legacy import)"],29  "languages": ["Swift", "Objective-C", "Python"],30  "source_model": "mixed",31  "license_spdx": "BSD-3-Clause",32  "pricing_model": ["free"],33  "self_hostable": false,34  "sources": [35    { "url": "https://developer.apple.com/documentation/coreml", "type": "official_site", "title": "Core ML | Apple Developer Documentation", "supports": ["name", "summary", "capabilities", "operating_systems"], "checked_at": "2026-11-02" },36    { "url": "https://apple.github.io/coremltools/docs-guides/", "type": "official_docs", "title": "Core ML Tools guide", "supports": ["capabilities", "data_formats", "integrations"], "checked_at": "2026-11-02" },37    { "url": "https://github.com/apple/coremltools", "type": "repository", "title": "apple/coremltools", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02", "note": "license_spdx refers to coremltools; the Core ML framework itself is proprietary" }38  ],39  "confidence": "high",40  "discovery_method": "editorial-research",41  "depth": "standard",42  "editorial_status": "reviewed",43  "visibility": "public",44  "featured": false,45  "author": "batch-C"46}47