TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Microsoft Foundry Local for Windows and Mac

6 pointsby MysticOracle4 days ago

2 comments

homarp4 days ago
Foundry Local is an on-device AI inference solution offering performance, privacy, customization, and cost advantages.<p>Optimize performance using ONNX Runtime and hardware acceleration, Foundry Local will automatically select and download a model variant with the best performance for your hardware. (CUDA if you have NVidia GPU, NPU-optimized model for Qualcomm NPU, and if nothing, CPU-optimized model)<p>Python and js SDK available.<p>If the model is not already available in ONNX, Olive (<a href="https:&#x2F;&#x2F;microsoft.github.io&#x2F;Olive&#x2F;" rel="nofollow">https:&#x2F;&#x2F;microsoft.github.io&#x2F;Olive&#x2F;</a>) allows to compile existing models in Safetensor or PyTorch format into the ONNX format<p>Foundry Local is licensed under the Microsoft Software License Terms
MysticOracle4 days ago
<a href="https:&#x2F;&#x2F;github.com&#x2F;microsoft&#x2F;Foundry-Local">https:&#x2F;&#x2F;github.com&#x2F;microsoft&#x2F;Foundry-Local</a><p><a href="https:&#x2F;&#x2F;devblogs.microsoft.com&#x2F;foundry&#x2F;unlock-instant-on-device-ai-with-foundry-local&#x2F;" rel="nofollow">https:&#x2F;&#x2F;devblogs.microsoft.com&#x2F;foundry&#x2F;unlock-instant-on-dev...</a>