<?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>Apple-Silicon on zolty.systems</title><link>https://blog.zolty.systems/tags/apple-silicon/</link><description>Recent content in Apple-Silicon on zolty.systems</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 13 Apr 2026 20:00:00 -0600</lastBuildDate><atom:link href="https://blog.zolty.systems/tags/apple-silicon/index.xml" rel="self" type="application/rss+xml"/><item><title>Running GLM-5.1 (744B) Locally on a Mac Studio: Benchmark Results</title><link>https://blog.zolty.systems/posts/2026-04-13-glm51-local-benchmark/</link><pubDate>Mon, 13 Apr 2026 20:00:00 -0600</pubDate><guid>https://blog.zolty.systems/posts/2026-04-13-glm51-local-benchmark/</guid><description>Benchmarking Z.ai&amp;#39;s 744B GLM-5.1 model locally on a Mac Studio M3 Ultra with 256GB unified memory via llama.cpp. Real numbers on speed, quality, and whether it&amp;#39;s worth the memory monopoly.</description></item></channel></rss>