NVIDIA Jetson AGX Orin 64GB Developer Kit with Ethernet, USB, Display Port

Many AI applications require ample memory to be effective. Most will buy into the RTX 4090 / 5090 range of cards for the desktop but will still hit memory limitations. For heavy duty needs and applications that route may be the best, as those routes have the most significant platform support and will shine where this does not. This means you must understand the limitations of the Jetson AGX Orin platform. It is a very capable one, but built upon older generations of nVidia architecture. This means that it is a bit slower than the latest generations when it comes to the tasks, which should be an acceptable trade-off given the low power and self-contained nature of the device. There is some finicky behavior getting the Jetson Container & linux environment onto the board as well. I would rate the 'ease of use' around 7/10. Do not cheap out on the USB-C cabling. You should also expect to buy an SSD. It isn't strictly required, but as you grab models or similar tasks, you'll fast chew through the 64GB onboard storage. Compatibility is where you are likely to get the most frustrated. Most of the major tools you might seek to use, ComfyUI, Stable Video Diffusion, etc. Suffer from Python dependency hell. Most modern apps get their code base tailored to the PC, which in turn leaves the Orin as a distant second though. There IS a community for the AGX Orin, but it's smaller than the RTX PC community. Mindset will decide whether this is a successful tool for you, or not. This is much more of a home-rolled AI development platform, than something you will find useful for just executing other folks' AI tools. If you're looking into AI development, this is definitely a solid and cost effective platform.

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.

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.

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

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.

I am revising my original review listed below and downgrading my review to one star. NVIDIA gas finally made available a version of their software that ships with Ubuntu 22, but it is not stable. After executing "apt upgrade" video drivers for the Orin lock up the Orin on reboots, making it unusable. I re-imaged my Orin twice and had the same issue. This is not a new problem for NVIDIA, as I observed the forums for th Oring. A company of NVIDIA's stature should be able to ship more reliable software for their hardware. There are far better options for $2K to the Orin, don't waster your money. Original review ------------------ Most reviewers of hardware drool the Orin hardware specs, and this device has impressive specs. Impressive hardware specs do not matter if there is limited support for the libraries. The NVIDIA Orin is frozen in time in terms of the most important libraries. For example, I use Python 3.11 for most things, but the only version that ships with this product is 3.8. NVIDIA provides versions of Python libraries, like Pytorch, that are needed to take advantage of the Orin GPU, but if you are stuck on Python 3.8, you will be limited in your ability to perform many if not most AI programming tasks. To that end, for support of Large Language Models (LLMs), you are better off running an Intel processor based machine with a GPU board. From a cost standpoint this is certainly cheaper. I realize this device is oriented towards image processing in support of IoT or Robotics projects. If you are processing images from an array of cameras, the Orin is a decent solution. As a platform for running local LLMs look elsewhere. Lastly, buyers need to be aware that if this Orin is to be re-flashed, or re-imaged, you really need to have an Intel based Linux machine, running Ubuntu 20!. I upgraded my Orin using the utility provided for this purpose. It is not easy and something only the most experienced pros can handle, IMHO.

This is a very powerful AI system. It's setup was very straight forward and it comes equipped with the full nVidia AI development stack. It runs Ubuntu 20.04 pre installed, and includes Docker. 64gb of main memory is more than sufficient. I added a 4TB SSD for additional storage. In addition to being a powerful AI system, it is also a fully loaded Linux workstation, and the nVidia GPU allows it to run large LLMs. If you are serious about getting involved with state of the art AI development, this system is an excellent choice.