<?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>Ml on Rusty Bower</title><link>https://www.rustybower.com/tags/ml/</link><description>Recent content in Ml on Rusty Bower</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 21 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.rustybower.com/tags/ml/index.xml" rel="self" type="application/rss+xml"/><item><title>Mac Studio as a Kubernetes Compute Satellite</title><link>https://www.rustybower.com/posts/mac-studio-kubernetes-compute-satellite/</link><pubDate>Tue, 21 Jul 2026 00:00:00 +0000</pubDate><guid>https://www.rustybower.com/posts/mac-studio-kubernetes-compute-satellite/</guid><description>&lt;p&gt;My K3s cluster runs on six Intel NUCs. They&amp;rsquo;re great for the 50+ containers that make up my homelab — Plex, Home Assistant, Frigate, Paperless, the usual suspects. But they&amp;rsquo;re terrible at machine learning. Four Skylake cores and 32 GB of RAM per node doesn&amp;rsquo;t get you far when Immich wants to classify 80,000 photos or Frigate wants a vision model to describe who&amp;rsquo;s at your door.&lt;/p&gt;
&lt;p&gt;The Mac Studio sitting under my desk — M1 Ultra, 64 GB unified memory — is the opposite problem. Absurd single-machine ML performance, but I don&amp;rsquo;t want to migrate my entire cluster to it. I want the K8s cluster to stay the control plane for routing, TLS, service discovery, and GitOps, while the Mac handles the heavy compute.&lt;/p&gt;</description></item></channel></rss>