<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Amd on homeio.org</title><link>https://homeio.org/tags/amd/</link><description>Recent content in Amd on homeio.org</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 20 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://homeio.org/tags/amd/feed.xml" rel="self" type="application/rss+xml"/><item><title>Running local LLMs on a Radeon AI PRO R9700: what actually made it faster</title><link>https://homeio.org/posts/2026/2026-11-20-radeon-r9700-local-llm-tuning/</link><pubDate>Fri, 20 Nov 2026 00:00:00 +0000</pubDate><guid>https://homeio.org/posts/2026/2026-11-20-radeon-r9700-local-llm-tuning/</guid><description>&lt;p&gt;I run my local models on one &lt;strong&gt;AMD Radeon AI PRO R9700 with 32 GB of VRAM&lt;/strong&gt;.
Over the last two months I measured what actually changes speed, memory fit and
energy use on this card, mostly while benchmarking coding agents.&lt;/p&gt;
&lt;p&gt;This post collects the tricks that held up under measurement, with numbers,
and two that did not. If you own an R9700, or another AMD card with llama.cpp,
most of this should transfer. &lt;strong&gt;I will keep updating it&lt;/strong&gt; as I measure more.&lt;/p&gt;</description></item></channel></rss>