<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>StartLux on GPT资讯  --  知识铺</title>
    <link>https://index.zshipu.com/gpt/tags/StartLux/</link>
    <description>Recent content in StartLux on GPT资讯  --  知识铺</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <lastBuildDate>Mon, 31 Aug 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://index.zshipu.com/gpt/tags/StartLux/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>StartLux-27B本地大模型性能超DeepSeek V4 Flash</title>
      <link>https://index.zshipu.com/gpt/post/20260831/StartLux-27B%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%80%A7%E8%83%BD%E8%B6%85DeepSeek-V4-Flash/</link>
      <pubDate>Mon, 31 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://index.zshipu.com/gpt/post/20260831/StartLux-27B%E6%9C%AC%E5%9C%B0%E5%A4%A7%E6%A8%A1%E5%9E%8B%E6%80%A7%E8%83%BD%E8%B6%85DeepSeek-V4-Flash/</guid>
      <description>StartLux-27B本地大模型性能超DeepSeek V4 Flash StartLux-27B在本地运行环境下多项指标超越DeepSeek V4 Flash，成为大模型领域的新玩家。这款27B参数模型无需依赖云端服务器，就能实现接近甚至超过更大规模云端模型的实际效果。 这款模型由新兴团队推出，直接</description>
    </item>
  </channel>
</rss>
