<?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>Moe on Aillex — Do-It-Yourself AI</title>
    <link>https://askaillex.com/tags/moe/</link>
    <description>Recent content in Moe on Aillex — Do-It-Yourself AI</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 29 Aug 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://askaillex.com/tags/moe/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Radar, 29 August: The Week Local AI Got Obsessed With Making Big Models Fit</title>
      <link>https://askaillex.com/articles/radar-hot-experts-vram-tricks/</link>
      <pubDate>Sat, 29 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://askaillex.com/articles/radar-hot-experts-vram-tricks/</guid>
      <description>Our news radar caught the same idea three different ways this week: people running mixture-of-experts models that do not fit their card, and finding tricks to run them anyway. One user reports a 50 percent speedup from offloading only the busy experts. Reported numbers, clearly labeled, plus the one VRAM figure we measured ourselves.</description>
    </item>
  </channel>
</rss>
