<?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>VRAM 24GB on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/vram-24gb/</link><description>Recent content in VRAM 24GB 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>Sun, 17 May 2026 06:59:04 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/vram-24gb/index.xml" rel="self" type="application/rss+xml"/><item><title>ローカルLLM用GPUの選び方｜Gemma 31Bを動かすRTX 4090 vs Mac比較</title><link>https://ai.negi-lab.com/posts/gemma-31b-local-llm-gpu-guide-rtx4090-mac/</link><pubDate>Sun, 17 May 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/gemma-31b-local-llm-gpu-guide-rtx4090-mac/</guid><description>Gemma 2 27Bベースの31Bモデルを実用レベルで動かすには、VRAM 24GB以上が絶対条件です。。RTX 4090を搭載したデスクトップPCか、...</description></item></channel></rss>