Skip to main content

List of Machine Learning, AI, NLP solutions for iOS. The most recent version of this article can be found on my blog.

1.4k
GitHub Stars
239
Curated Resources
21
Categories
6 hours ago
Last Refreshed
On-Device training and inferenceDeep Learning: Running pre-trained models on deviceDeep Learning: Low-level routines librariesDeep Learning: Model CompressionDeep LearningTraditional Computer VisionNLPOtherLinear algebraStatistics, random numbersMathematical optimizationFeature extractionData VisualizationBioinformatics (kinda)Big Data (not really)IPython + SwiftRegular mobile MLAccidental mobile MLMetalFree BooksFree Courses

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me deep learning: model compression resources from ios_ml"

Installation instructions →

What's inside

Deep Learning: Model Compression

Linear algebra

  • Accelerate-in-Swift

    Swift example codes for the Accelerate.framework

  • cuda-swift

    Swift binding to CUDA. Not iOS, but still interesting.

  • Dimensional

    Swift matrices with friendly semantics and a familiar interface.

  • Eigen

    A high-level C++ library of template headers for linear algebra, matrix and vector operations, numerical solvers and related algorithms. [MPL2]

  • Matrix

    convenient matrix type with different types of subscripts, custom operators and predefined matrices. A fork of Surge.

  • NDArray

    Float library for Swift, accelerated with Accelerate Framework.

Deep Learning: Low-level routines libraries

On-Device training and inference

  • another example

  • Birdbrain

    RNNs and FF NNs on top of Metal and Accelerate. Not ready for production.

  • BrainCore

    simple but fast neural network framework written in Swift. It uses Metal framework to be as fast as possible. ReLU, LSTM, L2 ...

  • Caffe

    another iOS port.

  • Caffe2

    a cross-platform framework made with expression, speed, and modularity in mind.

  • Caffe iOS sample

Showing a sample of 239 resources. View the full list on GitHub →