<?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>Needle2 on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/needle2/</link><description>Recent content in Needle2 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>Tue, 11 Aug 2026 06:53:43 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/needle2/index.xml" rel="self" type="application/rss+xml"/><item><title>ローカルLLM開発が変わるNeedle2登場！オンデバイスAI時代のハードウェア選び方とおすすめ比較</title><link>https://ai.negi-lab.com/posts/needle2-14mb-llm-on-device-hardware-guide/</link><pubDate>Tue, 11 Aug 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/needle2-14mb-llm-on-device-hardware-guide/</guid><description>Needle2は14MBという驚異的な軽さで、スマホやエッジ端末で「自律型エージェント」を動かすための救世主。。開発者は「巨大なVRAM」への投資だけでな...</description></item></channel></rss>