<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ubuntu on InternetException</title><link>https://internetexception.com/tags/ubuntu/</link><description>Recent content in Ubuntu on InternetException</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 16 Mar 2026 16:32:47 +0100</lastBuildDate><atom:link href="https://internetexception.com/tags/ubuntu/index.xml" rel="self" type="application/rss+xml"/><item><title>Running AI assistant on Qwen 3.5</title><link>https://internetexception.com/2026/03/15/running-ai-assistant-on-qwen-3-5/</link><pubDate>Sun, 15 Mar 2026 22:35:00 +0100</pubDate><guid>https://internetexception.com/2026/03/15/running-ai-assistant-on-qwen-3-5/</guid><description>&lt;p&gt;I did make mistake installing my favorite &lt;a href="https://internetexception.com/2026/03/13/switching-my-ai-assistant-os-to-ubuntu/"&gt;Debian Linux distribution on Desktop Framework&lt;/a&gt;&#10; PC I am using to run my LLM models. Probably some hacking during installing vLLM and all libraries and drivers and I would be able to make it work. But is it really worth it? I think it was not. So I switched to Ubuntu and I am &lt;a href="https://internetexception.com/2026/03/14/running-qwen-3-5-on-amd-ryzen-ai-max-395/"&gt;running Qwen 3.5&lt;/a&gt;&#10; second day now.&lt;/p&gt;&#10;&lt;p&gt;For now I can say that I am very happy. It seems to be able to reason much better than its predecessor Qwen 3. It have pretty good vision capabilities. It is able to fix its own mistakes, which makes its usage much easier.&lt;/p&gt;</description></item><item><title>Switching my AI assistant OS to Ubuntu</title><link>https://internetexception.com/2026/03/13/switching-my-ai-assistant-os-to-ubuntu/</link><pubDate>Fri, 13 Mar 2026 20:38:31 +0100</pubDate><guid>https://internetexception.com/2026/03/13/switching-my-ai-assistant-os-to-ubuntu/</guid><description>&lt;p&gt;I did make a mistake trying to run a vLLM server on Debian. I theory everything should be OK: Debian is stable, have docker, docker have images for vLLM so I should be able to run all the models on docker on Debian. Also it should not really matter what distro is as long as it have new kernel and docker works. That in theory. I practice I could not force some models to run and Qwen 3 even if it was capable enough it felt limiting at times. For example I was unable to force it to work in agentic loops. I am not sure what was the problem, probably some configuration issue that I am still unable to understand and fix. Still that was just a simple problem that required me to give my assistant some nudge with another prompt. It was not as bad another issue though.&lt;/p&gt;</description></item></channel></rss>