<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>GitLab on InternetException</title><link>https://internetexception.com/tags/gitlab/</link><description>Recent content in GitLab on InternetException</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 17 Aug 2026 17:27:09 +0200</lastBuildDate><atom:link href="https://internetexception.com/tags/gitlab/index.xml" rel="self" type="application/rss+xml"/><item><title>Short review of Qwen 3.8 27B</title><link>https://internetexception.com/2026/08/17/short-review-of-qwen-3-8-27b/</link><pubDate>Mon, 17 Aug 2026 17:27:09 +0200</pubDate><guid>https://internetexception.com/2026/08/17/short-review-of-qwen-3-8-27b/</guid><description>&lt;p&gt;&lt;a href="https://huggingface.co/Qwen/Qwen3.8-27B" target="_blank" rel="noopener noreferrer"&gt;Qwen 3.8&lt;/a&gt;&#10; is out since Friday, 17 of August. I am running it on my own server since Saturday. I am running &lt;a href="https://huggingface.co/unsloth/Qwen3.8-27B-GGUF" target="_blank" rel="noopener noreferrer"&gt;Q4 quants from unsloth&lt;/a&gt;&#10;.&lt;/p&gt;&#10;&lt;p&gt;So far it feels like a step up from Qwen 3.6 27B, which sometimes had problems figuring stuff in my project that I am developing almost entirely using models - just as a test of how far I can push LLMs in agentic coding - mostly local models, I must add. Qwen 3.8 seems like having no problem at all.&lt;/p&gt;</description></item></channel></rss>