metadata
license: agpl-3.0
library_name: coreml
pipeline_tag: object-detection
base_model: Ultralytics/YOLO11
base_model_relation: quantized
tags:
- coreml
- core-ml
- ios
- macos
- apple
- on-device
- yolo
- ultralytics
- real-time
YOLO11s — Core ML
Object Detection, 2024
YOLO11 small detection with Vision framework NMS. 640×640 input.
Core ML conversion of ultralytics/ultralytics for on-device inference on iPhone, iPad and Mac. Converted with coremltools; the packages are stateless, so all sequencing and buffering lives in your Swift code.
| Task | object detection |
| Upstream | ultralytics/ultralytics |
| Packages | 1 |
| Download size | 17 MB |
| Minimum iOS | 17.0 |
| Peak RAM | ~300 MB |
Files
| File | Size | Compute units | SHA-256 |
|---|---|---|---|
yolo11s.mlpackage.zip |
17 MB | all |
79e82aacc3ad20fc… |
| Total | 17 MB |
compute_units is not a suggestion -- it is the configuration the conversion was verified against. Moving a package to a different compute unit can silently change the numerics (FP16 attention overflow) or crash on the GPU.
Download
hf download mlboydaisuke/coreml-zoo --include "yolov9/*" --local-dir ./yolo11s
unzip './yolo11s/yolov9/*.zip' -d ./yolo11s
Use in Swift
import CoreML
let config = MLModelConfiguration()
config.computeUnits = .all // as converted — see the table above
// Unzip the .mlpackage, drop it into your Xcode target and Xcode compiles it
// at build time:
let model = try yolo11s(configuration: config)
// ...or compile a downloaded .mlpackage at runtime:
let compiled = try await MLModel.compileModel(at: mlpackageURL)
let model = try MLModel(contentsOf: compiled, configuration: config)
Demo
- Sample app —
sample_apps/YOLOv9Demo, a standalone SwiftUI project. - Models Zoo — this model is downloadable and runnable inside the Models Zoo app on the App Store, no build required.
Conversion
- Pitfalls hit during conversion (FP16 overflow, ANE buffer limits, stride handling):
docs/coreml_conversion_notes.md - Model index: CoreML-Models
License
The conversion inherits the upstream license: AGPL-3.0.
Credits
- Upstream authors: ultralytics/ultralytics, 2024
- Core ML conversion: john-rocky (Daisuke Majima)