<?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>Vscode on Hendrickx Consulting</title>
    <link>/tags/vscode/</link>
    <description>Recent content in Vscode on Hendrickx Consulting</description>
    <image>
      <title>Hendrickx Consulting</title>
      <url>/images/papermod-cover.png</url>
      <link>/images/papermod-cover.png</link>
    </image>
    <generator>Hugo</generator>
    <language>en-us</language>
    <copyright>Hendrickx Consulting</copyright>
    <lastBuildDate>Thu, 23 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="/tags/vscode/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Running a Local LLM on the Snapdragon NPU</title>
      <link>/posts/local-llm-snapdragon-npu/</link>
      <pubDate>Thu, 23 Jul 2026 00:00:00 +0000</pubDate>
      <guid>/posts/local-llm-snapdragon-npu/</guid>
      <description>&lt;p&gt;I picked up a Surface with a Snapdragon X Elite chip partly because of the on-device AI story. The NPU has 45 TOPS of compute, and Microsoft markets these devices specifically around local AI workloads. What I found when I actually tried to run a local LLM is that most of the popular tools completely ignore the NPU. Ollama runs on CPU only on ARM Windows. LM Studio does too, despite advertising GPU acceleration. The NPU just sits idle.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
