<?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>ローカルLLM 選び方 on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/%E3%83%AD%E3%83%BC%E3%82%AB%E3%83%ABllm-%E9%81%B8%E3%81%B3%E6%96%B9/</link><description>Recent content in ローカルLLM 選び方 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>Wed, 13 May 2026 07:20:59 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/%E3%83%AD%E3%83%BC%E3%82%AB%E3%83%ABllm-%E9%81%B8%E3%81%B3%E6%96%B9/index.xml" rel="self" type="application/rss+xml"/><item><title>ローカルLLMで1兆パラメータを動かす選び方｜Intel OptaneとGPUどっちを買うべきか比較</title><link>https://ai.negi-lab.com/posts/local-llm-1trillion-parameter-intel-optane-build/</link><pubDate>Wed, 13 May 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/local-llm-1trillion-parameter-intel-optane-build/</guid><description>結論: 超大規模モデル（1T超）を個人で動かすなら、GPU増設より「中古Xeon + Intel Optane PMem」構成が最も安上がり。。判断軸: ...</description></item></channel></rss>