<?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>MoE量化 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/moe%E9%87%8F%E5%8C%96/</link><description>Recent content in MoE量化 on AI 实战派 · 从技术到赚钱</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Thu, 15 Oct 2026 15:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/moe%E9%87%8F%E5%8C%96/index.xml" rel="self" type="application/rss+xml"/><item><title>英伟达 Nemotron 3.5 Bolt 74B 现身：24GB 显存跑 74B MoE，本地智能体要起飞</title><link>https://guijiagi.com/posts/2026-10-15-01-nemotron-35-bolt-74b-2bit-local/</link><pubDate>Thu, 15 Oct 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-15-01-nemotron-35-bolt-74b-2bit-local/</guid><description>Nemotron 3.5 Bolt 74B-A9B 以 2 bit 量化感知训练把 740 亿参数压进 24GB，面向本地智能体与 RTX Spark 桌面。</description></item></channel></rss>