<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[A custom fork for frontier-scale mixture-of-experts inference on an RTX 3060 with 12 GB VRAM, 16 GB system RAM and local NVMe]]></title><description><![CDATA[<em>This post did not contain any content.</em>

<div class="row mt-3"><div class="card col-md-9 col-lg-6 position-relative link-preview p-0">



<a href="https://github.com/Betelgeuse-AI/Betelgeuse" title="GitHub - Betelgeuse-AI/Betelgeuse: A custom fork for frontier-scale mixture-of-experts inference on an RTX 3060 with 12 GB VRAM, 16 GB system RAM and local NVMe.**  Betelgeuse keeps dense computation on the GPU and brings routed experts into a bounded VRAM pool only when needed.">
<img src="https://opengraph.githubassets.com/9a1cf611e976d496c05a793f8dc8106ce31fb6317b4c1ac2b93881aaee5655f8/Betelgeuse-AI/Betelgeuse" class="card-img-top not-responsive" style="max-height: 15rem;" alt="Link Preview Image" onerror="this.parentElement.remove()" />
</a>



<div class="card-body">
<h5 class="card-title">
<a class="text-decoration-none" href="https://github.com/Betelgeuse-AI/Betelgeuse">
GitHub - Betelgeuse-AI/Betelgeuse: A custom fork for frontier-scale mixture-of-experts inference on an RTX 3060 with 12 GB VRAM, 16 GB system RAM and local NVMe.**  Betelgeuse keeps dense computation on the GPU and brings routed experts into a bounded VRAM pool only when needed.
</a>
</h5>
<p class="card-text line-clamp-3">A custom fork for frontier-scale mixture-of-experts inference on an RTX 3060 with 12 GB VRAM, 16 GB system RAM and local NVMe.**  Betelgeuse keeps dense computation on the GPU and brings routed experts into a bounded VRAM pool only when needed.  - GitHub - Betelgeuse-AI/Betelgeuse: A custom fork for frontier-scale mixture-of-experts inference on an RTX 3060 with 12 GB VRAM, 16 GB system RAM and local NVMe.**  Betelgeuse keeps dense computation on the GPU and brings routed experts into a bounded VRAM pool only when needed.</p>
</div>
<a href="https://github.com/Betelgeuse-AI/Betelgeuse" class="card-footer text-body-secondary small d-flex gap-2 align-items-center lh-2">



<img src="https://github.githubassets.com/favicons/favicon.svg" alt="favicon" class="not-responsive overflow-hiddden" style="max-width: 21px; max-height: 21px;" onerror="this.remove()"/>



<p class="d-inline-block text-truncate mb-0">GitHub <span class="text-secondary">(github.com)</span></p>
</a>
</div></div>]]></description><link>https://citiverse.it/topic/1924a6f1-36e7-44a7-b592-2d459d59779e/a-custom-fork-for-frontier-scale-mixture-of-experts-inference-on-an-rtx-3060-with-12-gb-vram-16-gb-system-ram-and-local-nvme</link><generator>RSS for Node</generator><lastBuildDate>Fri, 20 Nov 2026 23:01:59 GMT</lastBuildDate><atom:link href="https://citiverse.it/topic/1924a6f1-36e7-44a7-b592-2d459d59779e.rss" rel="self" type="application/rss+xml"/><pubDate>Sat, 31 Oct 2026 20:22:37 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[Reply to A custom fork for frontier-scale mixture-of-experts inference on an RTX 3060 with 12 GB VRAM, 16 GB system RAM and local NVMe on Sat, 31 Oct 2026 22:55:08 GMT]]></title><description><![CDATA[<p dir="auto">I read the Github and I'm still not clear on what you would you from this that you wouldn't get from something like ik or croco.</p>
]]></description><link>https://citiverse.it/post/https://reddthat.com/comment/30049061</link><guid isPermaLink="true">https://citiverse.it/post/https://reddthat.com/comment/30049061</guid><dc:creator><![CDATA[swelter_spark@reddthat.com]]></dc:creator><pubDate>Sat, 31 Oct 2026 22:55:08 GMT</pubDate></item></channel></rss>