swift-transformers
Hugging Face's Swift package for tokenizers, model downloads and running models in Swift apps.
View on GitHub ↗- Stars
- ★ 1,360
- Last commit
- 14 Oct 2026
- Maintenance
- Active
- Licence
- Apache-2.0
- Category
- On-device AI SDKs
- GitHub
- huggingface/swift-transformers
Overview
swift-transformers from Hugging Face is a set of utilities for using language models in Swift apps. Its API will feel familiar to users of the Python transformers library while staying idiomatic Swift. The most used parts are Tokenizers and Hub, for fast tokenisation and model downloads.
Features
- Tokenisation and chat templating
- Formats inputs for tool calling
- Fast, reliable model downloads from the Hugging Face Hub
- Utilities for working with Core ML models and generation
- Offline tokenisers for bundled Core ML models
- Optional Xet trait for fast parallel downloads
Requirements
The source doesn't list any requirements, so check the project's own docs before you install.
Install
Add the package to Package.swift and add the Transformers product to your target
.package(url: "https://github.com/huggingface/swift-transformers", from: "1.3.0")
Works with
Listed in
- github.com/huggingface/swift-transformers
- raw.githubusercontent.com/huggingface/swift-transformers/HEAD/README.md
Read the code before you install anything. SwiftAgents doesn't review or endorse the tools listed here. Active: a commit in the last 90 days. Slowing: last commit within the past year. Stale: older than a year, or archived.