<?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/"><channel><title>Model Efficiency on 3rd layer</title><link>https://3rdlayer.uk/tags/model-efficiency/</link><description>Recent content in Model Efficiency on 3rd layer</description><generator>Hugo -- 0.157.0</generator><language>en-US</language><lastBuildDate>Sun, 04 Jan 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://3rdlayer.uk/tags/model-efficiency/index.xml" rel="self" type="application/rss+xml"/><item><title>The Model Efficiency series has moved to the company blog</title><link>https://3rdlayer.uk/posts/efficient-ml-resources/</link><pubDate>Sun, 04 Jan 2026 00:00:00 +0000</pubDate><guid>https://3rdlayer.uk/posts/efficient-ml-resources/</guid><description>The story of making neural networks smaller and faster (number formats, quantization, pruning, and so on) is now serialized on the company blog. Here is where to go.</description></item></channel></rss>