#4949th of 70 in Open models
coreml-models
Converted Core ML models for iOS and macOS, with sample apps
- Stars
- 1.9k
- License
- no license
- Last commit
- Oct 2026
- Last release
- Jun 2026
- Language
- Swift
1,724 on 21 Apr 20261,895 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A model zoo of pre-converted Core ML (.mlpackage) models covering image classification, object detection (YOLO, D-FINE, RF-DETR), segmentation, super resolution, depth, Stable Diffusion, TTS, source separation and small LLMs such as Gemma 4 and Qwen3.5. Models are downloaded from Google Drive or GitHub releases and bundled into an Xcode project, and some link to Swift sample apps. Each model keeps the license of its original project.
Who it is for: iOS and macOS developers who want ready-made on-device Core ML models
Strengths
- Wide coverage: vision, audio, diffusion and LLMs in one catalog of Core ML models
- Detector entries document input size, output shape and whether NMS is included
- Some models have Swift sample apps or Colab conversion scripts
- Used by xLights on macOS for HTDemucs stem separation
Weaknesses
- No repository license; each model follows its upstream license, including GPL and AGPL
- Many downloads are Google Drive links, which are hard to script or pin
- Apple platforms only; .mlpackage format, not the newer .aimodel format
- Sample apps cover only some models; many entries are download-only
What it needs
- Needs Xcode, Core ML
- Models: Core ML .mlpackage
Quick answers
Is coreml-models open source?
Its code is public on GitHub, but the repository has no license, so by default nobody may reuse it.
Also in Open models
See all 70| Rank | Project | Score |
|---|---|---|
| 1 | ruviewWiFi CSI sensing on ESP32 for presence, breathing, heart rate and pose | 94 out of 100 |
| 2 | layaSingle-pass multilingual classifier for typed choice, score and yes/no decisions | 88 out of 100 |
| 3 | rf-detrReal-time transformer models for object detection, segmentation and keypoints | 79 out of 100 |
| #4 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 78 out of 100 |
| #5 | yolov5PyTorch YOLOv5 object detection, segmentation and classification models with training code | 76 out of 100 |