mlboydaisuke/YOLOv10n-CoreML

YOLOv10n — Core ML

Object Detection, 2024

YOLOv10 nano. 640×640 input. Dual-assignment strategy.

Core ML conversion of THU-MIG/yolov10 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	THU-MIG/yolov10
Packages	1
Download size	4 MB
Minimum iOS	17.0
Peak RAM	~300 MB

Files

File	Size	Compute units	SHA-256
YOLOv10N.mlpackage.zip	4 MB	all	9a687144a6b0b764…
Total	4 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 "yolov10/*" --local-dir ./yolov10n
unzip './yolov10n/yolov10/*.zip' -d ./yolov10n

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 YOLOv10N(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/YOLOv10Demo, 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: THU-MIG/yolov10, 2024
• Core ML conversion: john-rocky (Daisuke Majima)