Microsoft has released 'Foundry Local,' an SDK that makes it easy to create apps that include local AI, allowing users to integrate the Qwen and Whisper series into their own applications.



Microsoft has released Foundry Local , an SDK for developing AI-powered apps. Foundry Local is compatible with Windows, macOS, and Linux, making it easy to develop apps that include AI models that can run on devices.

Foundry Local - Run AI Models On Device

https://www.foundrylocal.ai/

Foundry Local is a local AI solution that includes SDKs for C#, JavaScript, Python, and Rust, as well as a curated catalog of AI models. Foundry Local also features a function to scan the user's device configuration and detect available hardware acceleration, enabling the development of AI applications that can run without an internet connection.



The model catalog includes language models such as the 'gpt-oss series,' 'Qwen series,' 'DeepSeek series,' 'Mistral series,' and 'Phi series,' as well as the Whisper series of transcription AI. According to the documentation, the model catalog consists of 'models that have been tested on various hardware and are small enough to be distributed to users.' A model version control system is also integrated, allowing developers to choose between continuous model updates or fixed versions.



The Foundry Local documentation is available at the following link.

Foundry Local documentation | Microsoft Learn
https://learn.microsoft.com/en-us/azure/foundry-local/



A Japanese translation of the document is also available.

Foundry Local documentation | Microsoft Learn
https://learn.microsoft.com/ja-jp/azure/foundry-local/



Additionally, the source code for Foundry Local is available at the following link.

GitHub - microsoft/Foundry-Local · GitHub
https://github.com/microsoft/Foundry-Local



Related Posts:

in AI,   Software, Posted by log1o_hf