<?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>EdgeAI on TechLLM</title><link>https://techllm.github.io/tags/edgeai/</link><description>Recent content in EdgeAI on TechLLM</description><generator>Hugo</generator><language>ko</language><lastBuildDate>Sat, 02 May 2026 14:10:00 +0900</lastBuildDate><atom:link href="https://techllm.github.io/tags/edgeai/index.xml" rel="self" type="application/rss+xml"/><item><title>Gemma 4: 구글이 말하는 ‘파라미터 대비 성능’의 새 기준</title><link>https://techllm.github.io/posts/google-gemma-4-open-models/</link><pubDate>Sat, 02 May 2026 14:10:00 +0900</pubDate><guid>https://techllm.github.io/posts/google-gemma-4-open-models/</guid><description>Google Gemma 4 발표를 바탕으로, 오픈 모델이 에이전틱 워크플로우와 온디바이스 AI 개발에서 어떤 의미를 갖는지 정리한다.</description></item></channel></rss>