{"id":1301,"date":"2025-09-09T10:11:28","date_gmt":"2025-09-09T10:11:28","guid":{"rendered":"https:\/\/blog.aetherix.com\/?p=1301"},"modified":"2026-03-27T13:44:56","modified_gmt":"2026-03-27T13:44:56","slug":"how-to-run-ollama-on-jetson-agx-thor-with-openwebui","status":"publish","type":"post","link":"https:\/\/blog.openzeka.com\/en\/how-to-run-ollama-on-jetson-agx-thor-with-openwebui\/","title":{"rendered":"How to Run Ollama on Jetson AGX Thor with OpenwebUI?"},"content":{"rendered":"

What is Ollama?<\/h3><\/div>

Ollama is a lightweight and flexible platform that allows you to run large language models (LLMs) directly on your own device. When running on powerful AI hardware such as the NVIDIA Jetson AGX Thor<\/strong>, it provides a local, fast, and secure experience without the need for cloud-based solutions.<\/p>\n

Thanks to the high processing power of Jetson AGX Thor, Ollama:<\/p>\n

    \n
  • Runs LLMs locally<\/strong> \u2192 Can be used even without an internet connection.<\/li>\n
  • Utilizes hardware acceleration<\/strong> \u2192 Leverages GPU power to generate faster responses.<\/li>\n
  • Ensures data privacy<\/strong> \u2192 All processing happens on-device, so sensitive data never leaves the system.<\/li>\n
  • Offers flexibility<\/strong> \u2192 Different models can be downloaded, customized, and tested.<\/li>\n<\/ul>\n

    In short, Ollama leverages the hardware advantages of AGX Jetson Thor to make AI applications more accessible, portable, and secure.<\/p>\n<\/div>

    Requirements for AGX Thor<\/h3><\/div>
      \n
    1. JetPack 7 must be installed<\/li>\n
    2. Stable high-speed internet connection<\/li>\n
    3. At least 15 GB of free disk space (excluding model storage for Ollama itself)<\/li>\n<\/ol>\n<\/div>

      Installation Process<\/h3><\/div>

      First, we create a folder to mount into the container.<\/p>\n<\/div>