<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>Open Source LLMs Signals — VQV.me</title>
    <link>https://vqv.me/t/open-source-llms/</link>
    <description>Recent public signals for Open Source LLMs, refreshed every 4 hours.</description>
    <lastBuildDate>Thu, 18 Jun 2026 17:20:28 +0000</lastBuildDate>
    <atom:link xmlns:atom="http://www.w3.org/2005/Atom" href="https://vqv.me/t/open-source-llms/feed.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Show HN: Ironsmith – Generate personal native Mac apps with local LLMs</title>
      <link>https://vqv.me/t/open-source-llms/#signal-d272c53c8a</link>
      <guid>https://vqv.me/t/open-source-llms/#signal-d272c53c8a</guid>
      <pubDate>Thu, 18 Jun 2026 14:51:15 +0000</pubDate>
      <description>Hacker News discussion with 1 points and 1 comments. Why this is here: fresh within 24h + low-noise result. Source: Hacker News. Original: https://github.com/Jeidoban/Ironsmith</description>
      <category>WATCH</category>
    </item>
    <item>
      <title>Show HN: open source llm fusion</title>
      <link>https://vqv.me/t/open-source-llms/#signal-da317e31ec</link>
      <guid>https://vqv.me/t/open-source-llms/#signal-da317e31ec</guid>
      <pubDate>Thu, 18 Jun 2026 09:00:35 +0000</pubDate>
      <description>Hacker News discussion with 2 points and 0 comments. Why this is here: high signal strength + fresh within 24h + low-noise result. Source: Hacker News. Original: https://github.com/shahar-dagan/openfusion</description>
      <category>WATCH</category>
    </item>
    <item>
      <title>Two Qwen3 models on one DGX Spark: the residency math</title>
      <link>https://vqv.me/t/open-source-llms/#signal-353f01d11f</link>
      <guid>https://vqv.me/t/open-source-llms/#signal-353f01d11f</guid>
      <pubDate>Thu, 18 Jun 2026 16:29:52 +0000</pubDate>
      <description>Hacker News discussion with 2 points and 0 comments. Why this is here: fresh within 24h + low-noise result. Source: Hacker News. Original: https://www.devashish.me/p/two-qwen3-models-on-one-dgx-spark</description>
      <category>WATCH</category>
    </item>
    <item>
      <title>sebis at CRF Filling 2026: A Two-Stage Local LLM Pipeline for Medical CRF Filling</title>
      <link>https://vqv.me/t/open-source-llms/#signal-c596199b13</link>
      <guid>https://vqv.me/t/open-source-llms/#signal-c596199b13</guid>
      <pubDate>Thu, 11 Jun 2026 09:04:16 +0000</pubDate>
      <description>The extraction of structured clinical information from unstructured EHR notes is a persistent bottleneck in healthcare informatics. While large language models (LLMs) offer high performance, their deployment in clinical settings is hindered by privacy risks,... Why this is here: 95 signal strength + source-backed + low-noise result. Source: arXiv. Original: http://arxiv.org/abs/2606.13082v1</description>
      <category>WATCH</category>
    </item>
    <item>
      <title>Local Qwen isn't a worse Opus, it's a different tool</title>
      <link>https://vqv.me/t/open-source-llms/#signal-3c55c02dfe</link>
      <guid>https://vqv.me/t/open-source-llms/#signal-3c55c02dfe</guid>
      <pubDate>Wed, 17 Jun 2026 15:19:03 +0000</pubDate>
      <description>Hacker News discussion with 386 points and 214 comments. Why this is here: recent this week + low-noise result. Source: Hacker News. Original: https://blog.alexellis.io/local-ai-is-not-opus/</description>
      <category>WATCH</category>
    </item>
    <item>
      <title>Show HN: Pair your iPhone to your own Ollama over Tailscale with a QR scan</title>
      <link>https://vqv.me/t/open-source-llms/#signal-f52902d3ce</link>
      <guid>https://vqv.me/t/open-source-llms/#signal-f52902d3ce</guid>
      <pubDate>Tue, 16 Jun 2026 12:54:58 +0000</pubDate>
      <description>Hacker News discussion with 4 points and 0 comments. Why this is here: recent this week + low-noise result. Source: Hacker News. Original: https://github.com/TeamDzX/myllm-connect</description>
      <category>WATCH</category>
    </item>
  </channel>
</rss>
