---
title: README
emoji: 🤖
colorFrom: gray
colorTo: indigo
sdk: static
pinned: false
---

Welcome to the official Hugging Face organization for Apple!

## Apple Core ML – Build intelligence into your apps

[Core ML](https://developer.apple.com/machine-learning/core-ml/) is optimized for on-device performance of a broad variety of model types by leveraging Apple Silicon and minimizing memory footprint and power consumption.

* Models
  - [Depth Anything V2 Core ML](https://huggingface.co/collections/apple/core-ml-depth-anything-66727e780bc71c005763baf9): State-of-the-art depth estimation
  - [DETR Resnet50 Core ML](https://huggingface.co/apple/coreml-detr-semantic-segmentation): Semantic Segmentation
  - [FastViT Core ML](https://huggingface.co/collections/apple/core-ml-fastvit-666b782d98d6421a15237897): Image Classification  
  - [Stable Diffusion Core ML](https://huggingface.co/collections/apple/core-ml-stable-diffusion-666b3b0f4b5f3d33c67c6bbe)
  - [Additional Core ML Model Gallery Models](https://huggingface.co/collections/apple/core-ml-gallery-models-666b66ca4e6657b7d179bc42)

# Apple Machine Learning Research

Open research to enable the community to deliver amazing experiences that improve the lives of millions of people every day.

* Models
  - [DepthPro](https://huggingface.co/collections/apple/depthpro-models-66fee63b2f0dc1b231375ca6): State-of-the-art monocular depth estimation.
  - OpenELM [Base](https://huggingface.co/collections/apple/openelm-pretrained-models-6619ac6ca12a10bd0d0df89e) | [Instruct](https://huggingface.co/collections/apple/openelm-instruct-models-6619ad295d7ae9f868b759ca): open, Transformer-based language model. 
  - [MobileCLIP](https://huggingface.co/collections/apple/mobileclip-models-datacompdr-data-665789776e1aa2b59f35f7c8): Mobile-friendly image-text models.
  - [DCLM](https://huggingface.co/collections/apple/dclm-66960ebf2400d314ff19018f): State-of-the-art open data language models via dataset curation.
  - [DFN](https://huggingface.co/collections/apple/dfn-models-data-659ecf85cebd98088a9d9a3b): State-of-the-art open data CLIP models via dataset curation.


* Datasets
  - [FLAIR](https://huggingface.co/datasets/apple/flair): A large image dataset for federated learning.
  - [DataCompDR](https://huggingface.co/collections/apple/mobileclip-models-datacompdr-data-665789776e1aa2b59f35f7c8): Improved datasets for training image-text models.
* Benchmarks
  - [TiC-CLIP](https://huggingface.co/collections/apple/tic-clip-666097407ed2edff959276e0): Benchmark for the design of efficient continual learning of image-text models over years
 
# Select Highlights and Other Resources

- [Hugging Face CoreML Examples](https://github.com/huggingface/coreml-examples) – Run Core ML models with two lines of code!
- [Apple Model Gallery](https://developer.apple.com/machine-learning/models/)
- [New features in Core ML Tools](https://apple.github.io/coremltools/docs-guides/source/new-features.html) 
- [Apple Core ML Stable Diffusion](https://github.com/apple/ml-stable-diffusion) – Library to run Stable Diffusion on Apple Silicon with Core ML.
- Hugging Face Blog Posts
  - [WWDC 24: Running Mistral 7B with Core ML](https://huggingface.co/blog/mistral-coreml)
  - [Releasing Swift Transformers: Run On-Device LLMs in Apple Devices](https://huggingface.co/blog/swift-coreml-llm)
  - [Faster Stable Diffusion with Core ML on iPhone, iPad, and Mac](https://huggingface.co/blog/fast-diffusers-coreml)
  - [Using Stable Diffusion with Core ML on Apple Silicon](https://huggingface.co/blog/diffusers-coreml)