<?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>自作PC AI開発 on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/%E8%87%AA%E4%BD%9Cpc-ai%E9%96%8B%E7%99%BA/</link><description>Recent content in 自作PC AI開発 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, 21 Oct 2026 03:41:44 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/%E8%87%AA%E4%BD%9Cpc-ai%E9%96%8B%E7%99%BA/index.xml" rel="self" type="application/rss+xml"/><item><title>ローカルLLM用GPUの選び方：24GBの壁とNVIDIA Nemotronで変わる推奨スペック</title><link>https://ai.negi-lab.com/posts/local-llm-gpu-selection-24gb-vram-guide/</link><pubDate>Wed, 21 Oct 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/local-llm-gpu-selection-24gb-vram-guide/</guid><description>結論、実務レベルのローカルLLM運用には「VRAM 24GB（RTX 4090/3090）」が最低ラインの投資になる。NVIDIAの最新オープンモデル登場...</description></item></channel></rss>