NEWS · CODING · #2248
AnyLanguageModel 1.0 released with swift-huggingface and swift-xet 1.0, enabling local and hosted models on Apple platforms
AnyLanguageModel 1.0 is out alongside swift-huggingface 1.0 and swift-xet 1.0, offering a drop-in API that lets Swift apps on iOS, macOS, visionOS and Linux use Foundation Models-compatible local models (via llama.cpp, MLX, Core ML) or hosted providers (Hugging Face, Anthropic Messages API, OpenRouter and OpenAI-compatible endpoints). New features include guided generation across providers, image support using Foundation Models 27 syntax, reasoning transcript handling, short-lived API key closures, and migration guidance for existing apps.
KEY POINTS
- AnyLanguageModel 1.0 is out alongside swift-huggingface 1.0 and swift-xet 1.0, offering a drop-in API that lets Swift apps on iOS, macOS, visionOS and Linux use Foundation Models-compatible local models (via llama.cpp, MLX, Core ML) or hosted providers (Hugging Face, Anthropic Messages API, OpenRouter and OpenAI-compatible endpoints).
- New features include guided generation across providers, image support using Foundation Models 27 syntax, reasoning transcript handling, short-lived API key closures, and migration guidance for existing apps.
- This release simplifies developer choice between local and hosted inference on Apple platforms by unifying access via the Foundation Models API and adding cross-provider features and deployment options.
WHY IT MATTERS
This release simplifies developer choice between local and hosted inference on Apple platforms by unifying access via the Foundation Models API and adding cross-provider features and deployment options.