<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Gemma on Bluepie&#39;s Journal</title><link>//bluepie.in/categories/gemma/</link><description>Recent content in Gemma on Bluepie&#39;s Journal</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Sun, 12 Apr 2026 05:49:01 +0000</lastBuildDate><atom:link href="//bluepie.in/categories/gemma/index.xml" rel="self" type="application/rss+xml"/><item><title>Gemma4 - Easily running on phones - April 2026</title><link>//bluepie.in/2026/04/april-2026/</link><pubDate>Sun, 12 Apr 2026 05:49:01 +0000</pubDate><guid>//bluepie.in/2026/04/april-2026/</guid><description>Intro Today I want to talk about, Google Gemma 4; this sets a new standard for source AI models. I am astonished by the quality of this, though it has a small model size compared to the other big ones out there.. like Kimi K2.5 from Moonshot AI, that thing is a 1 trillion parameter model.. 1 trillion! and Gemma 4&amp;rsquo;s biggest is only 31 billion.. but here is the thing, Kimi K2.</description></item></channel></rss>