<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Notes from the gate on nimblegate</title>
    <link>https://nimblegate.com/blog/index.html</link>
    <description>Recent content in Notes from the gate on nimblegate</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Tue, 07 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://nimblegate.com/blog/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Running a local AI model smoothly on a $214 used office machine</title>
      <link>https://nimblegate.com/blog/local-ai-office-machine.html</link>
      <pubDate>Tue, 07 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://nimblegate.com/blog/local-ai-office-machine.html</guid>
      <description>&lt;p&gt;Can you run a local AI model smoothly on a used office machine that costs&#xA;about as much as one year of a chatbot subscription? I was skeptical. Then I&#xA;tried it, and the machine keeps surprising me. This post is the full setup&#xA;with real numbers, including the parts that are not impressive.&lt;/p&gt;&#xA;&lt;h2 id=&#34;the-machine&#34;&gt;The machine&lt;/h2&gt;&#xA;&lt;p&gt;A used mini PC with an i5-10400T: 6 cores, 35 W TDP, no GPU, SATA SSD. I paid&#xA;10,500 pesos for the box and 2,650 pesos for 2x16 GB of DDR4, about $214 total&#xA;at the time of writing.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
