<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>On-Device on Onur Baydaş</title><link>https://onurbaydas.com/en/tags/on-device/</link><description>Recent content in On-Device on Onur Baydaş</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 16 Oct 2026 00:17:33 +0300</lastBuildDate><atom:link href="https://onurbaydas.com/en/tags/on-device/index.xml" rel="self" type="application/rss+xml"/><item><title>Running Fast, Private Agents On-Device with LFM2.5-24B-A2B</title><link>https://onurbaydas.com/en/news/2026-10-16-lfm25-24b-a2b-on-device-agents/</link><pubDate>Fri, 16 Oct 2026 00:17:33 +0300</pubDate><guid>https://onurbaydas.com/en/news/2026-10-16-lfm25-24b-a2b-on-device-agents/</guid><description>Hugging Face announced the LFM2.5-24B-A2B model. This model enables AI agents to run directly on-device, offering fast and private operations.</description></item></channel></rss>