<?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>Hardware on Self-Hosted Tech</title><link>https://selfhostedtech.com/categories/hardware/</link><description>Recent content in Hardware on Self-Hosted Tech</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 15 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://selfhostedtech.com/categories/hardware/index.xml" rel="self" type="application/rss+xml"/><item><title>Best GPUs for Local LLMs in 2026: VRAM Tiers Explained</title><link>https://selfhostedtech.com/hardware/best-gpus-for-local-llms/</link><pubDate>Tue, 15 Sep 2026 00:00:00 +0000</pubDate><guid>https://selfhostedtech.com/hardware/best-gpus-for-local-llms/</guid><description>GPU buying guide for local AI in 2026. VRAM tiers, real-world benchmarks, used vs new, and which models actually run on each card.</description></item><item><title>I Replaced ChatGPT with a $351 Mini PC — Here's How</title><link>https://selfhostedtech.com/getting-started/replaced-chatgpt-with-mini-pc/</link><pubDate>Tue, 15 Sep 2026 00:00:00 +0000</pubDate><guid>https://selfhostedtech.com/getting-started/replaced-chatgpt-with-mini-pc/</guid><description>A complete walkthrough of building a $351 mini PC that runs local AI models, replaces ChatGPT, and pays for itself in 4 months.</description></item></channel></rss>