<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Gemma4 on Julien.cloud</title><link>https://julien.cloud/tags/gemma4/</link><description>Recent content in Gemma4 on Julien.cloud</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Julien</copyright><lastBuildDate>Tue, 09 Jun 2026 12:00:00 +0200</lastBuildDate><atom:link href="https://julien.cloud/tags/gemma4/index.xml" rel="self" type="application/rss+xml"/><item><title>Running Ollama on a Jetson Orin Nano: From Gemma 3 to Gemma 4 with GPU Acceleration</title><link>https://julien.cloud/blog/jetson-nano-ollama-edge-inference/</link><pubDate>Tue, 09 Jun 2026 12:00:00 +0200</pubDate><guid>https://julien.cloud/blog/jetson-nano-ollama-edge-inference/</guid><description>The journey from Gemma 3 4B (17.5 tok/s CPU) to Gemma 4 E2B (25.5 tok/s GPU) on the Jetson Orin Nano. Covers model testing, QAT quantization, the JetPack CUDA rabbithole, CMA traps, and the keepalive architecture that makes it all work.</description></item></channel></rss>