<?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>Cost on Onur Baydaş</title><link>https://onurbaydas.com/en/tags/cost/</link><description>Recent content in Cost on Onur Baydaş</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 19 Oct 2026 07:41:16 +0300</lastBuildDate><atom:link href="https://onurbaydas.com/en/tags/cost/index.xml" rel="self" type="application/rss+xml"/><item><title>Open Source LLM Weights and Hardware Requirements</title><link>https://onurbaydas.com/en/news/2026-10-19-open-llm-weights-hardware/</link><pubDate>Mon, 19 Oct 2026 07:41:16 +0300</pubDate><guid>https://onurbaydas.com/en/news/2026-10-19-open-llm-weights-hardware/</guid><description>Four major open-source LLM weight drops occurred in the last 72 hours, but only NVIDIA&amp;#39;s model fits into 24GB of GPU memory. Meta&amp;#39;s Muse Spark Open model has 816B total parameters and offers a 1M context window.</description></item></channel></rss>