| --- |
| license: apache-2.0 |
| library_name: coreml |
| pipeline_tag: object-detection |
| tags: |
| - coreml |
| - core-ml |
| - ios |
| - macos |
| - apple |
| - on-device |
| - detr |
| - transformer |
| - roboflow |
| - arxiv:2511.09554 |
| --- |
| |
| # RF-DETR Nano — Core ML |
|
|
| *Object Detection, 2025* |
|
|
| End-to-end transformer detector. 384×384 input. 300 queries, 91 classes (COCO + background). No NMS needed. |
|
|
| <p><img src="https://huggingface.co/mlboydaisuke/RF-DETR-Nano-CoreML/resolve/main/media/4d58781ec5.png" alt="RF-DETR Nano demo"></p> |
|
|
| Core ML conversion of [roboflow/rf-detr](https://github.com/roboflow/rf-detr) 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 | [roboflow/rf-detr](https://github.com/roboflow/rf-detr) | |
| | Packages | 1 | |
| | Download size | 95 MB | |
| | Minimum iOS | 17.0 | |
| | Peak RAM | ~400 MB | |
|
|
| ## Files |
|
|
| | File | Size | Compute units | SHA-256 | |
| |---|---:|---|---| |
| | `rfdetr_n_coco.mlpackage.zip` | 95 MB | `all` | `3cac3793b97aa88d…` | |
| | **Total** | **95 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 |
|
|
| ```bash |
| hf download mlboydaisuke/coreml-zoo --include "rfdetr/*" --local-dir ./rfdetr_n |
| unzip './rfdetr_n/rfdetr/*.zip' -d ./rfdetr_n |
| ``` |
|
|
| ## Use in Swift |
|
|
| ```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 rfdetr_n_coco(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** — [peaceofcake/DFINEDemo](https://github.com/john-rocky/peaceofcake/tree/main/DFINEDemo), a standalone iOS project. |
| - **Models Zoo** — this model is downloadable and runnable inside the [Models Zoo app](https://apps.apple.com/app/id6762083207) on the App Store, no build required. |
|
|
| ## Conversion |
|
|
| - Pitfalls hit during conversion (FP16 overflow, ANE buffer limits, stride handling): [`docs/coreml_conversion_notes.md`](https://github.com/john-rocky/CoreML-Models/blob/master/docs/coreml_conversion_notes.md) |
| - Model index: [CoreML-Models](https://github.com/john-rocky/CoreML-Models) |
|
|
| ## License |
|
|
| The conversion inherits the upstream license: **Apache-2.0**. |
|
|
| ## Credits |
|
|
| - Upstream authors: [roboflow/rf-detr](https://github.com/roboflow/rf-detr), 2025 |
| - Core ML conversion: john-rocky (Daisuke Majima) |
|
|
