<?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>Mac Studio on AI Pulse</title>
    <link>https://cuigh.com/tags/mac-studio/</link>
    <description>Recent content in Mac Studio on AI Pulse</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    <lastBuildDate>Wed, 17 Jun 2026 10:35:00 +0800</lastBuildDate>
    <atom:link href="https://cuigh.com/tags/mac-studio/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Local models are &#39;good now.&#39; Which line did we actually cross?</title>
      <link>https://cuigh.com/posts/local-models-good-now-2026/</link>
      <pubDate>Wed, 17 Jun 2026 10:35:00 +0800</pubDate>
      <guid>https://cuigh.com/posts/local-models-good-now-2026/</guid>
      <description>Vicki Boykis&amp;#39;s &amp;#39;Running local models is good now&amp;#39; hit HN #4 on June 16, 2026 at 1044 points and 437 comments, anchored by a 2022 M2 Mac with 64GB of RAM. Steipete&amp;#39;s 1443-like Mac Studio post, Amjad&amp;#39;s push for Mistral Le Chaton Fat, and Josh Woodward&amp;#39;s multilingual Gemini demo all line up with it. This is the first time &amp;#39;good enough&amp;#39; has stopped meaning &amp;#39;good enough to demo&amp;#39; and started meaning &amp;#39;good enough to ship a real workflow on.&amp;#39; I open up the three hidden arguments the 437 comments are actually having, and which ones I think hold up.</description>
    </item>
  </channel>
</rss>
