coremltools
Community Tools for Core ML
Decision gist · record as of 2026-08-14
Yes, if you are developing machine learning features for Apple platforms (iOS, macOS, watchOS, tvOS). coremltools is the standard tool for converting models to Core ML format and is actively maintained with no known vulnerabilities. Install friction is moderate due to multiple dependencies, but pre-built wheels are available for common platforms. Not relevant if you are not targeting Apple devices.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Conversion and prediction features require a trained model from a supported framework (e.g., TensorFlow, PyTorch, scikit-learn); prediction on Core ML models requires macOS, iOS, or compatible Apple platform.
- Medium install friction: pre-built wheels available for Python 3.7–3.13 on macOS (x86_64 and arm64) and Linux (x86_64), but 8 runtime dependencies (numpy, protobuf, sympy, tqdm, packaging, attrs, cattrs, pyaml) may require compilation or system libraries on some platforms.
- Active maintenance with recent commits.
License · maintenance · safety
BSD (permissive) — BSD 3-Clause license (permissive): you can use, modify, and distribute coremltools freely in commercial and open-source projects, provided you include the license notice and disclaimer.
last release 2025-11-10 (277 days) · last repo commit 2026-08-11 · 5,385 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,900,491 downloads/mo, #3,443 on PyPI
Alternatives
Verify before relying
pip install coremltools
import coremltools
# Convert a model (e.g., from a trained framework) to Core ML format
ml_model = coremltools.converters.convert(trained_model)
ml_model.save('model.mlmodel')- Which machine learning frameworks are supported for conversion (e.g., TensorFlow, PyTorch, scikit-learn, XGBoost).
- Whether prediction functionality works on Linux or only on Apple platforms.
- Specific version constraints or compatibility notes for numpy, protobuf, or other runtime dependencies.
What it is and what it does
coremltools is a Python package for working with Apple's Core ML format (.mlmodel), the standard for machine learning models on iOS, iPadOS, watchOS, macOS, and tvOS. It lets you convert trained models from popular ML frameworks into Core ML format, write models directly to .mlmodel using a simple API, and verify conversions by making predictions through the Core ML framework on supported platforms.
The package depends on numpy, protobuf, sympy, tqdm, packaging, attrs, cattrs, and pyaml to handle model serialization, computation, and data transformation. It is actively maintained, supports Python 3.7–3.13, and has pre-built wheels for macOS and Linux, making installation straightforward on most development machines. Core ML models can then be directly integrated into Xcode projects for deployment on Apple devices.
Use it for
- Convert a trained TensorFlow or PyTorch model to Core ML format for deployment in an iOS app.
- Export a scikit-learn decision tree or random forest to .mlmodel for use in a macOS application.
- Examine and validate a Core ML model's structure and metadata before shipping it to production.
- Test model predictions on macOS or iOS using the Core ML framework to verify conversion accuracy.
- Build a pipeline to automatically convert and package ML models for distribution via Xcode.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are developing machine learning features for Apple platforms (iOS, macOS, watchOS, tvOS).
coremltools is the standard tool for converting models to Core ML format and is actively maintained with no known vulnerabilities. Install friction is moderate due to multiple dependencies, but pre-built wheels are available for common platforms. Not relevant if you are not targeting Apple devices.
Install
coremltools on PyPI
Before you install
Medium install friction: pre-built wheels available for Python 3.7–3.13 on macOS (x86_64 and arm64) and Linux (x86_64), but 8 runtime dependencies (numpy, protobuf, sympy, tqdm, packaging, attrs, cattrs, pyaml) may require compilation or system libraries on some platforms. Active maintenance with recent commits.
Conversion and prediction features require a trained model from a supported framework (e.g., TensorFlow, PyTorch, scikit-learn); prediction on Core ML models requires macOS, iOS, or compatible Apple platform.
License in practice
BSD 3-Clause license (permissive): you can use, modify, and distribute coremltools freely in commercial and open-source projects, provided you include the license notice and disclaimer.
Quickstart
pip install coremltools
import coremltools
# Convert a model (e.g., from a trained framework) to Core ML format
ml_model = coremltools.converters.convert(trained_model)
ml_model.save('model.mlmodel')Verify before relying
- Which machine learning frameworks are supported for conversion (e.g., TensorFlow, PyTorch, scikit-learn, XGBoost).
- Whether prediction functionality works on Linux or only on Apple platforms.
- Specific version constraints or compatibility notes for numpy, protobuf, or other runtime dependencies.
Package facts
| License | BSD permissive |
| Python support | Not specified |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 8 packagesnumpyprotobufsympytqdmpackagingattrscattrspyaml |
| Maintenance | Actively maintained 277 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 1,900,491 / month, #3,443 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersOperating System :: MacOS :: MacOS XOperating System :: POSIX :: LinuxProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Scientific/EngineeringTopic :: Software Development |
Evidence: coremltools-9.0-cp310-none-macosx_10_15_x86_64.whl; coremltools-9.0-cp310-none-macosx_11_0_arm64.whl; coremltools-9.0-cp310-none-manylinux1_x86_64.whl; coremltools-9.0-cp311-none-macosx_10_15_x86_64.whl; coremltools-9.0-cp311-none-macosx_11_0_arm64.whl; coremltools-9.0-cp311-none-manylinux1_x86_64.whl; coremltools-9.0-cp312-none-macosx_10_15_x86_64.whl; coremltools-9.0-cp312-none-macosx_11_0_arm64.whl; coremltools-9.0-cp312-none-manylinux1_x86_64.whl; coremltools-9.0-cp313-none-macosx_10_15_x86_64.whl; coremltools-9.0-cp313-none-macosx_11_0_arm64.whl; coremltools-9.0-cp313-none-manylinux1_x86_64.whl; coremltools-9.0-cp37-none-macosx_10_15_x86_64.whl; coremltools-9.0-cp37-none-manylinux1_x86_64.whl; coremltools-9.0-cp38-none-macosx_10_15_x86_64.whl; coremltools-9.0-cp38-none-macosx_11_0_arm64.whl; coremltools-9.0-cp38-none-manylinux1_x86_64.whl; coremltools-9.0-cp39-none-macosx_10_15_x86_64.whl; coremltools-9.0-cp39-none-macosx_11_0_arm64.whl; coremltools-9.0-cp39-none-manylinux1_x86_64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “convert models to core ml format”
- coremltoolsConverts trained machine learning models from popular frameworks into…
- onnxmltoolsConverts machine learning models from multiple frameworks…
- litert-converterConverts machine learning models to LiteRT format for deployment on…
Give your agent the search over MCP, or paste the wish link into any chat.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also pyobjc-framework-CoreML · onnxmltools · azureml-train-core · treelite · keynote-parser · ai-edge-litert-nightly · pytabkit · tensorflow-decision-forests · azureml-core · interpret-core