Jetson AGX Orin 64GB Developer Kit

Really good platform for running LLM's. Every AI runner is optimized for CUDA and Nvidia, and the performance is really good. Also, the setup is fairly easy; pretty much everything just works. The unified memory works really well and you can run it headless or with a decent UI. You just have to decide if you can't live without the performance of the AGX Spark.

Very powerful device. Great for advanced projects and AI applications.

Marketing teams are expected to move fast, personalize messages, and use data to make better decisions. Most AI tools push everything to the cloud, which causes delays, higher costs, and concerns about data privacy. If you work in marketing, this is frustrating. You have good data and strong ideas, but the tools don’t fit how your team actually works, and AI ends up feeling more complicated than helpful. The NVIDIA Jetson AGX Orin 64GB Developer Kit gave us a reliable way to run AI on our own systems. We can analyze data, generate insights, and support campaigns locally, without depending on outside services or slow connections. Instead of testing AI in small experiments, we now use it as part of our daily marketing workflow. It supports planning, content, and analysis in a consistent and secure way. Our marketing efforts are faster, more organized, and more effective. This platform helped us turn AI into a practical tool we trust, not just another piece of technology to manage.

Item arrived exactly as described, brand new, factory sealed. Packaging was intact and the unit powered on without issues. Initial setup is straightforward: easy to connect to a monitor, keyboard, and mouse, and it boots immediately. That said, be aware this is older device. It ships with firmware and software last updated around 2023, which is expected, but important to know given how fast the AI ecosystem moves. To use it with modern AI frameworks, you’ll need to update the iGPU firmware, install a newer Jetson Linux release, and rebuild/install updated drivers and libraries. This isn’t plug-and-play for current AI workloads, but if you’re comfortable with Linux and system setup, it’s a great platform. I documented my full update and setup process in a Medium post for anyone interested.

I have been using this for a week now, and I love this device. It is a little slower than a proper GPU, but having this much memory available is what makes it good. Definitely add an NVMe drive. The 64 gigs of storage will disappear fast. This is a dev kit, so expect to spend a lot of time learning the tool set and make sure you use the torch versions from Nvidea. I have been able to run Framepack, ComfyUI (with several workflows), several LLMs, and SparkTTS so far. The only one that I haven't got working yet is Riva from one of the voice chat examples.