<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Gemma on TinyWeights.dev</title>
    <link>https://tinyweights.dev/tags/gemma/</link>
    <description>Recent content in Gemma on TinyWeights.dev</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sun, 24 May 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://tinyweights.dev/tags/gemma/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>MedGemma 1.5: Google&#39;s 4B Medical Vision-Language Model You Can Run Locally</title>
      <link>https://tinyweights.dev/posts/medgemma-1-5/</link>
      <pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
      <guid>https://tinyweights.dev/posts/medgemma-1-5/</guid>
      <description>MedGemma 1.5 is Google&amp;#39;s 4B medical multimodal model — Gemma 3 backbone, MedSigLIP encoder, 128K context. Runs in 3.3GB on Ollama. Benchmarks, deployment, and the limits.</description>
    </item>
  </channel>
</rss>
