<?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>メモリ帯域幅 on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/%E3%83%A1%E3%83%A2%E3%83%AA%E5%B8%AF%E5%9F%9F%E5%B9%85/</link><description>Recent content in メモリ帯域幅 on Negi AI Lab</description><image><title>Negi AI Lab</title><url>https://ai.negi-lab.com/images/og-default.png</url><link>https://ai.negi-lab.com/images/og-default.png</link></image><generator>Hugo -- 0.154.5</generator><language>ja</language><lastBuildDate>Thu, 01 Oct 2026 02:52:00 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/%E3%83%A1%E3%83%A2%E3%83%AA%E5%B8%AF%E5%9F%9F%E5%B9%85/index.xml" rel="self" type="application/rss+xml"/><item><title>AMD EPYC 256コア vs RTX 5090比較！ローカルLLM用PC選びと失敗しないメモリ帯域の知識</title><link>https://ai.negi-lab.com/posts/amd-epyc-256core-rtx5090-comparison-localllm/</link><pubDate>Thu, 01 Oct 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/amd-epyc-256core-rtx5090-comparison-localllm/</guid><description>新型EPYCはメモリ帯域1.6TB/sに到達し、RTX 5090の約91%という「CPU推論の限界」を突破した。。100Bパラメータを超える超巨大モデルを...</description></item></channel></rss>