# john-rocky/CoreML-Models

Core ML model zoo for iOS/macOS — PyTorch models converted to ready-to-use .mlpackage, each with a conversion script and SwiftUI sample app. Sibling repos cover Apple's Core AI framework (iOS/macOS 27) and on-device LLMs.

Repository: https://github.com/john-rocky/CoreML-Models
Canonical: https://ross.abutalabs.com/products/coreml-models
Homepage: https://john-rocky.github.io/
Language: Swift
License Family: other
Topics: coreml, coremltools, ios, swift, machine-learning, gan, deep-learning, object-detection, semantic-segmentation, super-resolution, apple-silicon, core-ai, mlpackage, on-device-ai
Last push: 2026-07-31T05:21:31+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 86, longevity 100
- inputs: {"age_days": 2212, "days_push": 33, "days_rel": 93, "gap_med": 0.0, "n_releases_24m": 19}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1851, forks 171 (observed 2026-08-28T04:05:44.348046+00:00)

## What it is
A curated model zoo of PyTorch models converted to ready-to-use CoreML .mlpackage files for iOS and macOS, each with a conversion script and SwiftUI sample app. It covers image classification, object detection, segmentation, super-resolution, style transfer, and more for on-device inference.

## Use cases
- run YOLO object detection on iPhone with CoreML
- convert PyTorch models to CoreML mlpackage
- on-device image segmentation for iOS app
- super resolution upscaler running on Apple Neural Engine
- find pre-converted CoreML models for iOS
- SwiftUI sample app for CoreML vision models
- background removal model for iOS

## When to choose
- you need ready-to-run CoreML models for iOS/macOS apps
- you want conversion scripts plus sample code for on-device ML
- you target Apple Neural Engine deployment of vision models

## When to avoid
- you target Android or non-Apple platforms (use TFLite/ONNX instead)
- you need server-side or cloud inference
- you require a permissively licensed dependency — the repo has no explicit license

## Facets
- artifact type: dataset
- maturity: active
- function: machine-learning, computer-vision, image-processing, deep-learning
- domain: machine-learning, computer-vision, image-processing, mobile-development, apple-ecosystem
- platform: cross-platform
- tags: coreml, model-zoo, mlpackage, on-device-ai, yolo, segmentation, super-resolution, neural-engine, swiftui, model-conversion, ios, macos, swift

## Member repositories
- john-rocky/CoreML-Models (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:44.348046+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 2026-08-30T03:16:55.591661+00:00, confidence not recorded.
  - readme: https://github.com/john-rocky/CoreML-Models (fetched 2026-08-28T04:05:44.348046+00:00, sha 8597f5f72ea9)
  - homepage: https://john-rocky.github.io/ (fetched 2026-08-29T10:56:04.192607+00:00, sha a6d09caa8308)
- Data as of 2026-08-30T08:39:29.467469+00:00.