<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llama-Cpp on mastori.dev</title><link>https://www.mastori.dev/tags/llama-cpp/</link><description>Recent content in Llama-Cpp on mastori.dev</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 mastori.dev</copyright><lastBuildDate>Wed, 21 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.mastori.dev/tags/llama-cpp/index.xml" rel="self" type="application/rss+xml"/><item><title>My PS5 Is Now the Local LLM Server for My House, and It Sleeps When I Don't Need It</title><link>https://www.mastori.dev/posts/ps5-local-llm-home-assistant/</link><pubDate>Wed, 21 Oct 2026 00:00:00 +0000</pubDate><guid>https://www.mastori.dev/posts/ps5-local-llm-home-assistant/</guid><description>The Relapse jailbreak opened every PS5 up to firmware 13.60. PS5LM turns one into a llama.cpp server with an OpenAI API. I ran five models on mine, measured them against Claude, wired the best one into Home Assistant, and wrote an integration that wakes the console when the house needs it and puts it back to sleep.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.mastori.dev/posts/ps5-local-llm-home-assistant/feature.svg"/></item></channel></rss>