<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: kofu</title><link>https://news.ycombinator.com/user?id=kofu</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 30 Jun 2026 21:23:38 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=kofu" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by kofu in "Qwen 3.6 27B is the sweet spot for local development"]]></title><description><![CDATA[
<p>My experience also aligns with this. I'm running gemma4 31B on a 4090 through llm.cpp with unsloth models.
I also run Qwen 3.6. Qwen is good for thinking and planning as it is faster, but Gemma4's generated code is much higher quality in the first try (Rust, C++ and C#). so it needs less revisions to be at a level I'm comfortable for merging.</p>
]]></description><pubDate>Mon, 29 Jun 2026 17:52:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=48722615</link><dc:creator>kofu</dc:creator><comments>https://news.ycombinator.com/item?id=48722615</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48722615</guid></item><item><title><![CDATA[New comment by kofu in "France dumps Zoom and Teams as Europe seeks digital autonomy from the US"]]></title><description><![CDATA[
<p>This one is often overlook but very good, I prefer it over Jitsi <a href="https://galene.org/" rel="nofollow">https://galene.org/</a></p>
]]></description><pubDate>Tue, 03 Feb 2026 18:01:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=46874568</link><dc:creator>kofu</dc:creator><comments>https://news.ycombinator.com/item?id=46874568</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46874568</guid></item></channel></rss>