<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>ai on Ground Bounce</title><link>https://groundbounce.com/tags/ai/</link><description>Recent content in ai on Ground Bounce</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 02 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://groundbounce.com/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Local AI inference on hardware I already had, and then a bit more</title><link>https://groundbounce.com/posts/local-ai-inference/</link><pubDate>Fri, 02 Oct 2026 00:00:00 +0000</pubDate><guid>https://groundbounce.com/posts/local-ai-inference/</guid><description>Running local LLMs and a RAG stack in a Proxmox VM: starting on a 6 GB GTX 1660 Ti, moving to a passed-through GTX 1060, and finally upgrading to an RTX 5060 Ti 16 GB, plus what changed at each step.</description></item></channel></rss>