<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hardware on SchifanoIA</title><link>https://schifanoia.jesimiron.eu/en/categories/hardware/</link><description>Recent content in Hardware on SchifanoIA</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Gian Paolo Jesi</copyright><lastBuildDate>Fri, 05 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://schifanoia.jesimiron.eu/en/categories/hardware/index.xml" rel="self" type="application/rss+xml"/><item><title>A cheap but effective computer</title><link>https://schifanoia.jesimiron.eu/en/blog/2026/06/05/game2aipc/</link><pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate><guid>https://schifanoia.jesimiron.eu/en/blog/2026/06/05/game2aipc/</guid><description>&lt;p&gt;Like every computer scientist or enthusiast, over the years I&amp;rsquo;ve&#10;piled up an impressive number of components: CPUs, memory, disks,&#10;cases, power supplies and boards of every kind.&lt;/p&gt;&#10;&lt;p&gt;Anything more than 10 years old is considered obsolete, and yet these components are&#10;still perfectly functional and can run almost anything decently.&#10;Does that apply to AI models too? Definitely not!&lt;/p&gt;&#10;&lt;p&gt;But there is a loophole: what matters is the GPU, because the LLM runs entirely there.&#10;The rest of the machine doesn&amp;rsquo;t need to be particularly sophisticated.&lt;/p&gt;</description></item></channel></rss>