<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>Self-hosted Intelligence</title>
  <subtitle>Benchmarks for the AI you run yourself.</subtitle>
  <id>https://selfhostedintelligence.com/</id>
  <link rel="self" type="application/atom+xml" href="https://selfhostedintelligence.com/en/feed.xml"/>
  <link rel="alternate" type="text/html" href="https://selfhostedintelligence.com/"/>
  <updated>2026-10-13T00:00:00Z</updated>
  <entry>
    <title>Round-trip translation benchmark v26.10.0 published</title>
    <id>https://selfhostedintelligence.com/en/benchmarks/rtt/v2610</id>
    <link rel="alternate" type="text/html" href="https://selfhostedintelligence.com/en/benchmarks/rtt/v2610"/>
    <published>2026-10-13T00:00:00Z</published>
    <updated>2026-10-13T00:00:00Z</updated>
    <summary>The first leaderboard of the round-trip translation benchmark is out. It compares self-hosted open models and their quantisations, with and without reasoning, and shows the memory each needs at each context size and the relative cost of each run.</summary>
  </entry>
</feed>
