<?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>MTPLX on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/mtplx/</link><description>Recent content in MTPLX 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, 20 Aug 2026 02:27:19 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/mtplx/index.xml" rel="self" type="application/rss+xml"/><item><title>MTPLXで変わるMac選び｜ローカルLLMが3倍速くなる時代のApple Siliconおすすめ構成と失敗しない買い方</title><link>https://ai.negi-lab.com/posts/mtplx-mlx-apple-silicon-high-speed-llm/</link><pubDate>Thu, 20 Aug 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/mtplx-mlx-apple-silicon-high-speed-llm/</guid><description>Apple Silicon専用の高速化技術「MTPLX」により、MacでのLLM推論速度が最大3倍に向上する。。外部モデル不要のMTP（Multi-Tok...</description></item></channel></rss>