<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Qwen on Greycloak</title><link>https://greycloak.com/tags/qwen/</link><description>Recent content in Qwen on Greycloak</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><copyright>Copyright © 2023, Vince Wadhwani; all rights reserved.</copyright><lastBuildDate>Sat, 14 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://greycloak.com/tags/qwen/index.xml" rel="self" type="application/rss+xml"/><item><title>Can my laptop stand in for Claude Haiku?</title><link>https://greycloak.com/post/2026-11-14-can-my-laptop-stand-in-for-claude-haiku/</link><pubDate>Sat, 14 Nov 2026 00:00:00 +0000</pubDate><guid>https://greycloak.com/post/2026-11-14-can-my-laptop-stand-in-for-claude-haiku/</guid><description>
I set up a local AI model on my laptop's integrated graphics and gave it the basics a cloud model has: today's date, web search, a view of the computer it runs on, and a memory. It works and nothing leaves the machine unless it searches, but a web question takes two minutes. Here's the setup, what slowed it down, and where I'd use it.</description></item></channel></rss>