http://www.lineon.fr/tags/ollama/Recent content in Ollama on Clean TechHugoenSun, 15 Mar 2026 00:00:00 +0000http://www.lineon.fr/posts/deploying-ollama-on-jetson-nano/Sun, 15 Mar 2026 00:00:00 +0000http://www.lineon.fr/posts/deploying-ollama-on-jetson-nano/<p>Running large language models locally is no longer reserved for beefy GPU rigs. With the right setup, a Jetson Nano can serve as a surprisingly capable inference endpoint for smaller models — completely air-gapped from the cloud.</p> <h2 id="why-edge-inference-matters">Why edge inference matters</h2> <p>For security professionals, running models locally means:</p> <ul> <li><strong>No data exfiltration risk</strong> — queries never leave your network</li> <li><strong>Predictable latency</strong> — no API rate limits or outages</li> <li><strong>Full control</strong> — choose your model, quantization, and context length</li> </ul> <h2 id="hardware-requirements">Hardware requirements</h2> <table> <thead> <tr> <th>Component</th> <th>Specification</th> </tr> </thead> <tbody> <tr> <td>Board</td> <td>NVIDIA Jetson Nano (4GB)</td> </tr> <tr> <td>Storage</td> <td>64GB+ microSD (A2 rated)</td> </tr> <tr> <td>Power</td> <td>5V 4A barrel jack (not USB)</td> </tr> <tr> <td>Cooling</td> <td>Active fan recommended</td> </tr> </tbody> </table> <h2 id="installation">Installation</h2> <p>First, flash JetPack 4.6 and update the system:</p>