<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: yuweiloopy2</title><link>https://news.ycombinator.com/user?id=yuweiloopy2</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 30 Apr 2026 10:33:41 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=yuweiloopy2" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by yuweiloopy2 in "Gemma 3 QAT Models: Bringing AI to Consumer GPUs"]]></title><description><![CDATA[
<p>Been using the 27B QAT model for batch processing 50K+ internal documents. The 128K context is game-changing for our legal review pipeline. Though I wish the token generation was faster - at 20tps it's still too slow for interactive use compared to Claude Opus.</p>
]]></description><pubDate>Mon, 21 Apr 2025 13:26:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=43751784</link><dc:creator>yuweiloopy2</dc:creator><comments>https://news.ycombinator.com/item?id=43751784</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43751784</guid></item></channel></rss>