<?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>Llama 3.3 on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/llama-3.3/</link><description>Recent content in Llama 3.3 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>Sat, 16 May 2026 07:08:28 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/llama-3.3/index.xml" rel="self" type="application/rss+xml"/><item><title>ローカルLLM選びの新基準！ollamatps.comで判明した「速度×賢さ」の最適解と推奨ハードウェア比較</title><link>https://ai.negi-lab.com/posts/ollama-tps-intelligence-model-comparison-hardware-guide/</link><pubDate>Sat, 16 May 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/ollama-tps-intelligence-model-comparison-hardware-guide/</guid><description>ローカルLLM運用は「賢さ」だけでなく「TPS（速度）」とのバランスが実務効率を左右する。最新データではGLM-4.7とLlama 3.3 70Bが「賢い...</description></item></channel></rss>