<?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/" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>Llm on Sebastian Zehner</title><link>https://sebastianzehner.com/tags/llm/</link><description>Recent content in Llm on Sebastian Zehner</description><generator>Hugo</generator><language>en</language><managingEditor>blog@techlab.icu (Sebastian Zehner)</managingEditor><webMaster>blog@techlab.icu (Sebastian Zehner)</webMaster><copyright>&lt;span class='custom-footer-icon'&gt;&lt;/span&gt;2026 Sebastian Zehner</copyright><lastBuildDate>Sat, 10 Jan 2026 22:20:00 +0000</lastBuildDate><atom:link href="https://sebastianzehner.com/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Optimizing the Ollama Context Window: The key to a successful integration of OpenCode</title><link>https://sebastianzehner.com/posts/ollama-context-window-optimization-opencode/</link><pubDate>Sat, 10 Jan 2026 22:20:00 +0000</pubDate><author>blog@techlab.icu (Sebastian Zehner)</author><guid>https://sebastianzehner.com/posts/ollama-context-window-optimization-opencode/</guid><category>ollama</category><category>llm</category><category>opencode</category><category>open-source</category><category>terminal</category><enclosure url="https://sebastianzehner.com/posts/ollama-context-window-optimization-opencode/featured.webp" type="image/webp" length="0"/><media:content url="https://sebastianzehner.com/posts/ollama-context-window-optimization-opencode/featured.webp" medium="image"/><description>The Context Window is the “invisible bottleneck” in many Ollama setups. Here are three approaches to optimize its performance, practical tests using various models, and specific recommendations for successfully integrating OpenCode with LLMs.</description></item><item><title>The challenges of multilingual blogs</title><link>https://sebastianzehner.com/posts/md-translator/</link><pubDate>Wed, 17 Dec 2025 20:00:00 +0000</pubDate><author>blog@techlab.icu (Sebastian Zehner)</author><guid>https://sebastianzehner.com/posts/md-translator/</guid><category>hugo</category><category>markdown</category><category>blogging</category><category>ai</category><category>llm</category><category>claude</category><enclosure url="https://sebastianzehner.com/posts/md-translator/featured.webp" type="image/webp" length="0"/><media:content url="https://sebastianzehner.com/posts/md-translator/featured.webp" medium="image"/><description>Multilingual blogs incur translation costs. Manual translations are expensive, while automated tools often damage the Markdown format. How can one still remain efficient and preserve the original format?</description></item></channel></rss>