<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Benchmarking on /sys/admin/blog</title><link>https://kre80r.com/tags/benchmarking/</link><description>Recent content in Benchmarking on /sys/admin/blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 31 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://kre80r.com/tags/benchmarking/feed.xml" rel="self" type="application/rss+xml"/><item><title>Two cards, too many variables</title><link>https://kre80r.com/two-cards-too-many-variables/</link><pubDate>Mon, 31 Aug 2026 00:00:00 +0000</pubDate><guid>https://kre80r.com/two-cards-too-many-variables/</guid><description>&lt;p>In April I rented a machine with two RTX 3090s on Vast.ai, to see what a second
card would buy me before paying for one. On the first benchmark, two cards were
21 times slower per token than one. My write-up that day ended with &amp;ldquo;Don&amp;rsquo;t buy a
2nd 3090 for the local rig right now.&amp;rdquo;&lt;/p></description></item></channel></rss>