<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>FreeToken on KAD</title>
    <link>https://www.kad8.com/tags/freetoken/</link>
    <description>Recent content in FreeToken on KAD</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>© 2026 </copyright>
    <lastBuildDate>Sat, 22 Aug 2026 22:25:16 +0800</lastBuildDate><atom:link href="https://www.kad8.com/tags/freetoken/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>FreeToken Lets a Single RTX 5090 Run 284B MoE Models Locally</title>
      <link>https://www.kad8.com/ai/freetoken-lets-a-single-rtx-5090-run-284b-moe-models-locally/</link>
      <pubDate>Sat, 22 Aug 2026 22:25:16 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/freetoken-lets-a-single-rtx-5090-run-284b-moe-models-locally/</guid>
      <description>&lt;blockquote&gt;
&lt;p&gt;FreeToken Lets a Single RTX 5090 Run 284B MoE Models Locally&lt;/p&gt;&lt;/blockquote&gt;
&lt;p&gt;Running frontier-scale language models locally has traditionally been constrained by one fundamental problem: the model may be open-weight, but the hardware required to serve it is not.&lt;/p&gt;</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/freetoken-lets-a-single-rtx-5090-run-284b-moe-models-locally/featured-FreeToken_runs_models_on_GPUs.jpeg" />
    </item>
    
  </channel>
</rss>
