<?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>Hetzner on disobey.dev</title><link>https://disobey.dev/tags/hetzner/</link><description>Recent content in Hetzner on disobey.dev</description><generator>Hugo -- 0.152.2</generator><language>en-us</language><lastBuildDate>Wed, 19 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://disobey.dev/tags/hetzner/index.xml" rel="self" type="application/rss+xml"/><item><title>Using hetzner's free inference in your coding agent</title><link>https://disobey.dev/posts/hetzner-free-inference-coding-agent-config/</link><pubDate>Wed, 19 Aug 2026 00:00:00 +0000</pubDate><guid>https://disobey.dev/posts/hetzner-free-inference-coding-agent-config/</guid><description>&lt;p&gt;Hetzner is &lt;a href="https://experiments.hetzner.com/docs/inference"&gt;offering some free inference&lt;/a&gt; and since free tokens are always welcome it would be a shame not to give the models for a spin. Specially since they now offer Qwen3.8-27B for free, which is perfect for those who don&amp;rsquo;t have enough local compute to run it themselves (or those who need more tokens - and who doesnt).&lt;/p&gt;
&lt;p&gt;Below are examples for two agents I regularly&lt;/p&gt;
&lt;h2 id="pi-configuration"&gt;Pi configuration&lt;/h2&gt;
&lt;p&gt;cat ~/.pi/agent/models.json&lt;/p&gt;</description></item></channel></rss>