<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Mixture of Experts on Linky Systems</title><link>https://linkysystems.com/en/tags/mixture-of-experts/</link><description>Recent content in Mixture of Experts on Linky Systems</description><generator>Hugo</generator><language>en</language><lastBuildDate>Thu, 15 Oct 2026 01:30:00 -0300</lastBuildDate><atom:link href="https://linkysystems.com/en/tags/mixture-of-experts/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Fundamentals: Dense Models vs MoE - Linky Systems</title><link>https://linkysystems.com/en/blog/2026/10/15/2026-10-15-ai-fundamentals-dense-models-vs-moe/</link><pubDate>Thu, 15 Oct 2026 01:30:00 -0300</pubDate><guid>https://linkysystems.com/en/blog/2026/10/15/2026-10-15-ai-fundamentals-dense-models-vs-moe/</guid><description>&lt;h1 id="ai-fundamentals-dense-models-vs-moe"&gt;AI Fundamentals: Dense Models vs MoE&lt;/h1&gt;
&lt;p&gt;&lt;a href="https://linkysystems.com/en/blog/2026/10/05/2026-10-05-ai-fundamentals-nlp-and-nlu/"&gt;The previous article&lt;/a&gt; covered NLP and NLU, the conceptual field behind language models. This last one closes the series by going back to architecture: the difference between dense models and MoE, which parameters are actually activated for each token, and why that changes the math on cost and memory, a topic that had already come up in the &lt;a href="https://linkysystems.com/en/blog/2026/09/22/2026-09-22-ai-fundamentals-training-inference-and-quantization/"&gt;article on quantization and local use&lt;/a&gt;.&lt;/p&gt;</description></item></channel></rss>