<?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>Mps on zolty.systems</title><link>https://blog.zolty.systems/tags/mps/</link><description>Recent content in Mps on zolty.systems</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 04 Jun 2026 19:00:00 -0400</lastBuildDate><atom:link href="https://blog.zolty.systems/tags/mps/index.xml" rel="self" type="application/rss+xml"/><item><title>The Mac Studio as a GPU appliance: serving Ollama and ComfyUI to a k3s cluster</title><link>https://blog.zolty.systems/posts/2026-06-04-mac-studio-gpu-appliance/</link><pubDate>Thu, 04 Jun 2026 19:00:00 -0400</pubDate><guid>https://blog.zolty.systems/posts/2026-06-04-mac-studio-gpu-appliance/</guid><description>Running a Mac Studio M3 Ultra as a headless GPU host for local LLM inference and image generation, proxied into a k3s cluster, with 256 GB of unified memory split between Ollama and ComfyUI.</description></item></channel></rss>