<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI on Elias G.</title><link>https://grabuge.me/fr/categories/ai/</link><description>Recent content in AI on Elias G.</description><generator>Hugo</generator><language>fr-FR</language><copyright>© Elias G.</copyright><lastBuildDate>Mon, 29 Dec 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://grabuge.me/fr/categories/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Running a local LLM on a Jetson Orin Nano</title><link>https://grabuge.me/fr/posts/local-jetson-llm/</link><pubDate>Mon, 29 Dec 2025 00:00:00 +0000</pubDate><guid>https://grabuge.me/fr/posts/local-jetson-llm/</guid><description>&lt;p&gt;&lt;img src="https://grabuge.me/assets/img/posts/llm.png" alt="web ui"&gt;&lt;/p&gt;
&lt;h2 id="why-run-an-llm-locally"&gt;Why run an LLM locally?&lt;/h2&gt;
&lt;p&gt;Running a Large Language Model on your own hardware gives you full control over your data, zero API costs, and the ability to use AI offline. The Nvidia Jetson Orin Nano is a compact yet powerful device perfect for this use case.&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;What you&amp;rsquo;ll need:&lt;/strong&gt;&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Nvidia Jetson Orin Nano (8GB RAM recommended)&lt;/li&gt;
&lt;li&gt;MicroSD card (64GB+) or NVMe SSD&lt;/li&gt;
&lt;li&gt;Power supply (5V 4A or higher)&lt;/li&gt;
&lt;li&gt;Internet connection for initial setup&lt;/li&gt;
&lt;/ul&gt;
&lt;h2 id="setup"&gt;Setup&lt;/h2&gt;
&lt;p&gt;Ollama is the easiest way to run LLMs locally. It handles model downloads, quantization, and provides a simple API.&lt;/p&gt;</description></item></channel></rss>