mlboydaisuke/YOLO26s-CoreML

YOLO26s — Core ML

NMS-Free Detection, 2026

NMS-free object detection. 640×640 input, 80 COCO classes.

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
yolo26s.mlpackage.zip	17 MB	all	0ec02fb0cf2dbd6e…
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 "yolo26/*" --local-dir ./yolo26s
unzip './yolo26s/yolo26/*.zip' -d ./yolo26s

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 yolo26s(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/YOLO26Demo, 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, 2026
• Core ML conversion: john-rocky (Daisuke Majima)