<?xml version="1.0" encoding="UTF-8"?>
  <rss version="2.0">
    <channel>
      <title>AICoreShop</title>
      <link>https://aicoreshop.com</link>
      <description>Practical guides for AI creation, local AI setups, and useful tools. Learn what works, understand the trade-offs, and build with confidence.</description>
      <language>en-us</language>
      <lastBuildDate>Wed, 21 Oct 2026 05:58:50 GMT</lastBuildDate>
      
      <item>
        <title>Can a 32GB RTX 4080 SUPER Run MiniMax H3 Locally? A ComfyUI Test</title>
        <link>https://aicoreshop.com/articles/minimax-h3-rtx-4080-super-32gb-comfyui/</link>
        <guid isPermaLink="true">https://aicoreshop.com/articles/minimax-h3-rtx-4080-super-32gb-comfyui/</guid>
        <description>MiniMax H3&apos;s ComfyUI model files total 39.55 GB. On a modified 32GB RTX 4080 SUPER, 864×480 clips took about 148 s and a 1920×1088 clip took 53 minutes without running out of memory.</description>
        <pubDate>Wed, 21 Oct 2026 00:00:00 GMT</pubDate>
      </item>
      <item>
        <title>Can a 16GB RTX 5060 Ti Run MiniMax H3 at 1080p? A ComfyUI Test</title>
        <link>https://aicoreshop.com/articles/minimax-h3-rtx-5060-ti-16gb-1080p/</link>
        <guid isPermaLink="true">https://aicoreshop.com/articles/minimax-h3-rtx-5060-ti-16gb-1080p/</guid>
        <description>MiniMax H3&apos;s model files total 39.55 GB. On an RTX 5060 Ti 16GB with 32 GB of RAM, 864×480 clips took about 294 s, and a 5-second 1920×1088 clip finished in about 72 minutes.</description>
        <pubDate>Wed, 21 Oct 2026 00:00:00 GMT</pubDate>
      </item>
      <item>
        <title>Same RTX 5060 Ti, New PC: Why a 27B Local LLM Ran 164% Faster</title>
        <link>https://aicoreshop.com/articles/rtx-5060-ti-platform-upgrade-27b-llm/</link>
        <guid isPermaLink="true">https://aicoreshop.com/articles/rtx-5060-ti-platform-upgrade-27b-llm/</guid>
        <description>We moved an RTX 5060 Ti 16GB from an old X99 workstation to a Z790 DDR5 PC. A 27B model that spills out of VRAM sped up 164%; a 12B model that fits gained 18%.</description>
        <pubDate>Wed, 21 Oct 2026 00:00:00 GMT</pubDate>
      </item>
    </channel>
  </rss>