# apple/coremltools

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

Repository: https://github.com/apple/coremltools
Canonical: https://ross.abutalabs.com/products/coremltools
Homepage: https://coremltools.readme.io
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: coremltools, tensorflow, pytorch, coreml, machine-learning, model-converter, model-conversion
Last push: 2026-08-26T19:25:12+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 44, longevity 100
- inputs: {"age_days": 3351, "days_push": 7, "days_rel": 296, "gap_med": 80.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5399, forks 836 (observed 2026-08-28T04:09:17.407113+00:00)

## What it is
Apple's official Python package for converting machine learning models from TensorFlow, PyTorch, scikit-learn, XGBoost, and LibSVM into the Core ML format. It also supports reading, editing, optimizing, and validating Core ML models for on-device deployment in Apple apps.

## Use cases
- convert a pytorch model to core ml format
- deploy a trained tensorflow model on iphone
- optimize a core ml model for the neural engine
- convert a scikit-learn model for ios app integration
- edit and validate an existing core ml model
- run on-device inference with core ml in an xcode app

## When to choose
- you need to ship trained models to iOS, macOS, watchOS, or visionOS apps via Core ML
- you want Apple-supported conversion from PyTorch or TensorFlow with Neural Engine optimization
- you need to inspect, edit, or compress Core ML model weights

## When to avoid
- you target Android, Windows, or Linux on-device inference rather than Apple platforms
- you need a general model exchange format like ONNX instead of Core ML
- your workflow is training-only with no Apple deployment

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, sdk, developer-tools
- domain: machine-learning, apple-ecosystem, deep-learning
- platform: python, cross-platform
- tags: coreml, model-conversion, model-optimization, tensorflow, pytorch, on-device-inference, apple, macos

## Member repositories
- apple/coremltools (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:17.407113+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:57:49.138673+00:00, confidence not recorded.
  - readme: https://github.com/apple/coremltools (fetched 2026-08-28T04:09:17.407113+00:00, sha 45afb380a2aa)
  - homepage: https://coremltools.readme.io (fetched 2026-08-29T08:52:34.380912+00:00, sha 3b9d5e7ed62f)
  - site_page: https://coremltools.readme.io/docs (fetched 2026-08-29T08:52:34.383643+00:00, sha 9a24c31bd62e)
- Data as of 2026-08-30T08:39:29.467469+00:00.