<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llm on Ilya Brin - Software Engineer</title><link>https://ilyabrin.github.io/tags/llm/</link><description>Recent content in Llm on Ilya Brin - Software Engineer</description><generator>Hugo</generator><language>en</language><lastBuildDate>Wed, 29 Apr 2026 10:00:00 +0300</lastBuildDate><atom:link href="https://ilyabrin.github.io/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM Quantization Types: a Cheat Sheet</title><link>https://ilyabrin.github.io/post/llm-quantization-guide/</link><pubDate>Wed, 29 Apr 2026 10:00:00 +0300</pubDate><guid>https://ilyabrin.github.io/post/llm-quantization-guide/</guid><description>&lt;p&gt;Trying to run a large language model locally but not sure which file to download? Q4_K_M, IQ3_S, Q5_K_M - these aren&amp;rsquo;t random strings. They describe the quantization format, which determines response quality and how much memory the model will use.&lt;/p&gt;</description></item></channel></rss>