Tools · SPBoucher
Menu

Core ML

by Apple Inc. · Framework · also known as CoreML, coremltools

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

BSD-3-Clause licenseFreeLocal
Visit official site Compare

Link verified Nov 2, 2026

Overview

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.

Models 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.

Core 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.

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

Typical workflows

  1. Convert a PyTorch classifier and ship it in an iOS app
  2. Profile a model's latency per compute unit in Xcode
  3. Run image analysis offline with Vision on top of Core ML

Strengths

  • Inference stays on the device; no network or server cost
  • Hardware scheduling handled by the system
  • Open-source conversion tooling

Limitations

  • Apple platforms only
  • Not a training framework
  • Unsupported operators block conversion
  • Large models constrained by device memory

Prerequisites

  • Xcode and an Apple platform target
  • Python with coremltools for conversion

Who it is for

  • iOS and macOS developers embedding ML
  • ML engineers deploying models to Apple devices

Alternatives & comparison

  • Create ML

    Apple's app and Swift framework for training image, text, sound, tabular and activity models on a Mac without writing training code, exporting directly to Core ML

    ProprietaryFree
  • Foundation Models (Apple)

    Apple's Swift framework giving apps access to the on-device Apple Intelligence language model with guided generation, tool calling and sessions, on OS 26 and later

    ProprietaryFree
  • llama.cpp

    C/C++ inference engine for LLMs and vision-language models with GGUF quantized weights, Metal, CUDA, Vulkan and other backends, a CLI and an OpenAI-compatible server

    Open sourceOpen source
  • MLX

    Apple's open-source array framework for machine learning on Apple Silicon, with NumPy-like Python, C++ and Swift APIs and unified CPU/GPU memory

    Open sourceOpen source
  • PyTorch

    Open-source deep-learning framework with eager tensors, autograd, torch.compile and distributed training, governed by the PyTorch Foundation and the base of most LLM tooling

    Open sourceOpen source
Compare Core ML with its alternatives →

Sources & verification

Primary sources consulted for this record. Claims are tied to the fields each source supports; the automated link checker re-verifies every URL on a schedule.

  • Official documentation
    Core ML Tools guide

    https://apple.github.io/coremltools/docs-guides

    Supports: capabilities, data_formats, integrations

    checked Nov 1, 2026
  • Official documentation
    Core ML | Apple Developer Documentation

    https://developer.apple.com/documentation/coreml

    Supports: name, summary, capabilities, operating_systems

    checked Nov 1, 2026
  • Repository
    apple/coremltools

    https://github.com/apple/coremltools

    Supports: license_spdx, source_model

    license_spdx refers to coremltools; the Core ML framework itself is proprietary

    checked Nov 1, 2026
Confidence
High
Reviewed
Nov 1, 2026
Links
Verified · Nov 2, 2026

Spotted an error?

Broken link, outdated license, wrong category, or a tool that no longer exists? Tell us; reports are reviewed by the editor.

LM Studio

Element Labs, Inc. · Local LLM inference & serving

In-depth entry

Proprietary desktop app for discovering, downloading and running local LLMs with llama.cpp and MLX engines, a chat UI, an OpenAI-compatible server, CLI, SDKs and a headless daemon

ProprietaryFreemiumPaidLocalBroken

MLX LM

Apple Inc. · Apple Silicon ML & MLX

In-depth entry

Python package and CLI for running, serving, quantizing and fine-tuning large language models on Apple Silicon with MLX

MITOpen sourceFreeLocalNov 2, 2026

Ollama

Ollama · Local LLM inference & serving

In-depth entry

Open-source runtime and model manager for running open-weight LLMs locally on macOS, Windows and Linux, with a REST API, OpenAI- and Anthropic-compatible endpoints and optional cloud models

MITOpen sourceFreeLocalSelf-hostedNov 2, 2026

Metal

Apple Inc. · Apple Silicon ML & MLX

Apple's low-level GPU programming framework for graphics and parallel compute on iOS, macOS and visionOS, the layer beneath MLX, Core ML and most Apple Silicon ML runtimes

ProprietaryFreeLocalNov 2, 2026

Create ML

Apple Inc. · Apple Silicon ML & MLX

Apple's app and Swift framework for training image, text, sound, tabular and activity models on a Mac without writing training code, exporting directly to Core ML

ProprietaryFreeLocalNov 2, 2026

exo

Exo Labs · Distributed & parallel computing

Open-source software that pools several Apple Silicon Macs (and Linux hosts) into one local inference cluster, sharding large models across devices with MLX

Apache-2.0Open sourceFreeLocalSelf-hostedNov 2, 2026