Core ML Tools
Convert TensorFlow, PyTorch, and scikit-learn models to Core ML for Apple devices.
About
Core ML Tools is Apple's official Python package for converting trained models from frameworks like TensorFlow, PyTorch, scikit-learn, and XGBoost into Core ML, the on-device ML format used across iPhone, iPad, Mac, Apple Watch, and Apple TV. Converted models run locally on the CPU, GPU, or Neural Engine, so inference stays fast and private with no server round trip.
Beyond conversion, it includes utilities for inspecting models, composing pipelines, and validating outputs against the original framework. It is the standard bridge between a Python training workflow and shipping an ML feature inside an Apple app, and it is free and open source.
What it can do
- Convert TF, PyTorch, scikit-learn, and XGBoost models to Core ML
- On-device inference on CPU, GPU, and Neural Engine
- Model inspection and pipeline composition
- Validation of converted model outputs
Setup
Install with pip: pip install coremltools.
Prerequisites
Python 3 and a trained model in a supported framework.
Use cases
Works with
Trust score — 6/10
Scored 6/10 (metrics tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 86; Trending score 62/100 from researcher assessment.
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.