<?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>Llm on derek.engineer</title>
    <link>https://derek.engineer/tags/llm/</link>
    <description>Recent content in Llm on derek.engineer</description>
    <image>
      <title>derek.engineer</title>
      <url>https://derek.engineer/og-default.png</url>
      <link>https://derek.engineer/og-default.png</link>
    </image>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 09 Oct 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://derek.engineer/tags/llm/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>What Limits Local AI Speed on an Arduino, a Raspberry Pi and a Mac Mini</title>
      <link>https://derek.engineer/posts/what-limits-local-ai-speed/</link>
      <pubDate>Fri, 09 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://derek.engineer/posts/what-limits-local-ai-speed/</guid>
      <description>Two weeks of measurements on an Arduino UNO Q, a Raspberry Pi 5 and a Mac mini M4, backed by real data: what limits how fast a small language model runs, where the usual rules hold and where they break, and what a token costs in energy.</description>
    </item>
  </channel>
</rss>
