<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Ai on </title>
    <link>https://namesny.com/tags/ai/</link>
    <description>Recent content in Ai on </description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 04 Feb 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://namesny.com/tags/ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Building an AI Homelab</title>
      <link>https://namesny.com/blog/homelab/</link>
      <pubDate>Wed, 04 Feb 2026 00:00:00 +0000</pubDate>
      <guid>https://namesny.com/blog/homelab/</guid>
      <description>&lt;p&gt;As part of my job over the past year, I&amp;rsquo;ve been deploying and evaluating LLMs locally on various hardware setups. Naturally, I became well versed in the open source tools and models available and various hardware options. So I decided to build my own homelab for local inference.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Llama-Server is (Almost) All You Need</title>
      <link>https://namesny.com/blog/llamactl/</link>
      <pubDate>Thu, 04 Sep 2025 00:00:00 +0000</pubDate>
      <guid>https://namesny.com/blog/llamactl/</guid>
      <description>&lt;p&gt;If you&amp;rsquo;re running LLMs locally, you&amp;rsquo;ve probably used Ollama or LM Studio. But they are effectively wrappers for llama.cpp. They’re convenient, but they impose limits that get in the way once you start trying to squeeze maximum performance out of your hardware.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
