Hugging Face releases AnyLanguageModel 1.0 for Swift apps on Apple platforms
Hugging Face announced AnyLanguageModel 1.0, a Swift library that lets iOS, macOS, visionOS and Linux apps use local or hosted language models through a shared Foundation Models API. The update adds tool calling, guided generation (including nested @Generable types) and image support for all providers, and moves API‑key handling to closures for short‑lived tokens.
Key points
- AnyLanguageModel 1.0 adds tool calling, guided generation, and image support across all providers.
- Supports OpenAI, Anthropic, Google Gemini, Ollama, Private Cloud Compute, Hugging Face Inference and OpenRouter via unified API.
- Popular downloadable models include Gemma 4 E2B (3.4 GB), LFM2.5 2.6B (1.7 GB), Qwen3.8 27B (16 GB) and GLM‑5.3 (1.5 TB).
The library now works with OpenAI’s Chat Completions, Anthropic’s Messages, Google’s Gemini, Ollama, Private Cloud Compute, Hugging Face Inference Providers and OpenRouter endpoints. Local models can run via llama.cpp, MLX or Core ML, while larger open‑weight models can be accessed through the Inference Providers layer. Popular downloadable models listed on the Hub include Gemma 4 E2B (≈3.4 GB), LFM2.5 2.6B (≈1.7 GB), Qwen3.8 27B (≈16 GB) and GLM‑5.3 (≈1.5 TB). Swift‑huggingface 1.0 and swift‑xet 1.0 also ship to accelerate model downloads. Migration guidance is provided for developers updating existing apps.
Model page: GLM 5.3 →
The story so far
3 episodes →- Hugging Face releases AnyLanguageModel 1.0 for Swift apps on Apple platformsthis story
AnyLanguageModel 1.0: One Year of Local Models on Apple Platforms
Hugging Face · 20 October 2026
Loading the full article…
This text was published by Hugging Face and written by Mattt. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- U.S. Army develops echotribble program to deploy autonomous AI agents for cyber attacks · 3 src
- Avenda Health launches Surgery Mode for intraoperative use of Unfold AI · 1 src
- Microsoft introduces Guardian Agents to monitor AI agents as insider threats · 5 src
- Accenture expands federal AI push with Google's Gemini agents · 4 src
- Ben builds an all-in-one app for personal AI agents · 1 src
Comments
via GitHub Discussions