Microsoft has launched Foundry Local, a versatile SDK for creating AI-powered applications compatible with Windows, macOS, and Linux. This local AI solution enables developers to build applications that leverage AI models directly on devices, eliminating the need for internet connectivity. Foundry Local supports languages like C#, JavaScript, Python, and Rust, and features a curated catalog of AI models, including the ‘gpt-oss series,’ ‘Qwen series,’ ‘DeepSeek series,’ ‘Mistral series,’ and ‘Phi series,’ as well as transcription capabilities from the Whisper series. Notably, it includes a hardware acceleration scanning feature for optimal performance. Developers can utilize a model version control system for flexibility with updates. Comprehensive documentation is available on Microsoft Learn, including a Japanese translation. Access the source code via GitHub to explore and enhance local AI applications further. For more information, visit Foundry Local and explore the documentation.
