Apple Core ML Runtime
AppleApple Core ML is an on-device inference runtime that executes models across Apple's CPU, GPU, and Neural Engine, shipped as a system framework with iOS, macOS, watchOS, tvOS, and visionOS. It partitions model graphs across the available hardware and runs .mlpackage and .mlmodel files, which the separately distributed coremltools package produces. Apple's own on-device features, including Apple Intelligence, are built on it.
Openness
1 high confidence- source
- closed
- license
- proprietary(Apple system framework, ships compiled with the OS/SDK, no published source)
- self-host
- no
Core ML has no public repository. Apple's documentation describes it only as an API surface, such as MLModel, that an app calls into, with no source tree to self-host or fork.
- https://developer.apple.com/tutorials/data/documentation/coreml.md recorded 2026-09-23
Use Core ML to integrate machine learning models into your app... Copyright © 2026 Apple Inc. All rights reserved.
Adoption
5 medium confidenceCore ML ships as a system framework across iOS, iPadOS, macOS, tvOS, watchOS and visionOS, reaching the full installed base of Apple hardware rather than a discrete set of developers. The adoption figure is Apple's own count of active devices from its earnings calls, which counts hardware rather than actual invocations of Core ML.
- https://docs.developer.apple.com/tutorials/data/documentation/coreml/mlmodel.md recorded 2026-09-29
"availability" : [ "iOS: 11.0.0 -", "iPadOS: 11.0.0 -", "macCatalyst: 13.1.0 -", "macOS: 10.13.0 -", "tvOS: 11.0.0 -", "visionOS: 1.0.0 -", "watchOS: 4.0.0 -" ]
- https://sixcolors.com/post/2026/07/one-last-time-this-is-tim-transcript-of-apples-q3-2026-financial-call/ recorded 2026-09-29
The Q3 2026 earnings call transcript has Apple stating an "installed base of over two and a half billion active devices has reached another all-time high".
Capability
4 medium confidenceBest in class for on-device and edge inference, with Neural Engine acceleration, quantization and palettization, and broad coverage of converted models, but constrained to Apple silicon and to on-device scale. That places it one tier below the large-scale server engines, of which vLLM holds the top capability score in this category.
- https://apple.github.io/coremltools/docs-guides/source/opt-overview.html recorded 2026-09-29
The coremltools optimization overview states "Core ML supports INT4 and INT8 quantization options for weights and INT8 for activations."
- https://docs.developer.apple.com/tutorials/data/documentation/coreml.md recorded 2026-09-29
The Core ML documentation home page says the framework runs models "leveraging the CPU, GPU, and Neural Engine while minimizing its memory footprint and power consumption".
Verified 2026-09-23