🚀 Elevate Your AI Game with Jetson Orin Nano!
The NVIDIA Jetson Orin Nano Super Developer Kit is a cutting-edge, compact computing platform designed for generative AI applications in edge devices. With 67 TOPS of AI performance, an 8GB RAM module, and a versatile carrier board, it supports a wide array of AI applications and is backed by NVIDIA's robust software ecosystem. Ideal for developers looking to prototype next-gen AI solutions, this kit offers unmatched performance and efficiency.
Processor | athlon |
Wireless Type | Bluetooth |
Brand | NVIDIA |
Series | Jetson Orin Nano 8GB |
Item model number | 945-137766-0000-000 |
Operating System | Linux |
Item Weight | 2.33 pounds |
Product Dimensions | 3.94 x 3.11 x 0.83 inches |
Item Dimensions LxWxH | 3.94 x 3.11 x 0.83 inches |
Processor Brand | ARM |
Number of Processors | 1 |
Manufacturer | NVIDIA |
ASIN | B0BZJTQ5YP |
Date First Available | March 21, 2023 |
R**.
Clever toy
I like the nice packaging and the organized looks of the board. It seems to me that they really listened to the customers when designing this board. And all in all it is worth the money because of that little plastic caret around the board. This is very practical. I appreciate as well the wifi board, so I don't have to worry about compatibility of an addon board.The software part was not new to me since I am used to NVIDIA tools. I bought this one for hobby use and faced the situation of flashing this device from a Fedora Linux host. It took me about a day to get it flashed the hard way, that is no sd/card, but an SSD and sdkmanager tool.Booting it with an SDcard would have been simple, but I didn't want to have the slowdown that is reported with that mode.BTW this board supports PXE-Boot, so I wonder what can it boot that way.In my case, the flashing has still some installs todo but the system already runs and I see the GUI. This is good enough for starting development.Accessories - I wish more house options would pop up. For now it will get an end2end DIY housing.
S**E
Be careful. The sd imaging doesn't work and the sdkmanager is very particular
The board works great but it took a few days of experimentation to get it to flash.Make sure to use a jumper cable between the reset pin and the ground pin (located under the fan module on the outside of the board). Plug the display port on the board into a monitor while you are using the sdk manager. At any point if there is activity on the external monitor, let that finish before you continue in the sdk manager.
N**A
Absolutely awesome
I have this one to complement my nano as well as my raspberry pi 5’s and 4’s. Orin is awesome its fast and works great for my robotics projects. Crazy fast……
K**B
Absolutely nightmare to flash SD card, wasted over 2 days - too late to return
you cant use ubuntu 22. Was not able to upgrade firmware. SDK manager takes forever and most modules fail. I came back to view the reviews here and found that everyone else had these issues. Wasted $500. Not even sure if this unit is original Nvidia. Firmware version showing 0.0.1 (sudo nvbootctrl dump-slots-info) instead of something like 35.5.0
L**N
Good hardware. Not user friendly. Install Jetpack 5 not 6
After 4 days I finally got this running. The hardware is powerful for something so small. But honestly, it was nightmare to set this up because of the crappy software. First of all, the Jetpack 6 OS doesn't flash for models built before May 2024 unless you first install Jetpack 5 to update the firmware. And even then, Jetpack 6 only works on SD cards at this time, not on NVME drives. To use an NVME drive, you need to use Jetpack 5.1.13.... But nobody mentioned this in the docs. I had to delete Ubuntu 22 and install Ubuntu 20 on a laptop to successfully flash the Jetson. Also installing Pytorch and OpenCV with GPU support was a horrible experience. If you do it wrong, there will be no GPU support or some arcane error will happen. There are a lot of little dumb things. For example, Bluetooth Audio is disabled by default and you have to go to this random file to enable it again in order to use Bluetooth speakers or headphones. Visual Studio Code is not available on the Store. You have to search on somebody's website to download it.Eventually I did get it running like a normal Ubuntu computer with a GPU and I love it. But if I hadn't already thrown out the box and 3D printed a case for it... Probably would have just returned it.What the Dev team at Nvidia needs to do is to streamline and simplify the process so out of the box so that this thing operates like a cool minicomputer that you just boot up and use and then can later modify for robotics work. I had to search various YouTube videos, and internet forums to get this running... If I wasn't already experienced with Linux, and computer vision stuff... This product would have been impossible to use.
A**R
There is a steep learning curve!
Beware of the fake Jetson Orin Nanos being sold by unscrupulous sellers, but if you get a genuine one, like I did, you will be impressed by its power. What you are paying for is the ability to learn the same NVIDIA AI stack used by the ultra high-end, ultra expensive systems.I was able to run a smallish LLM model on it using OLLAMA and it was quite fast. For me that was worth the hassle. Because this is bleeding edge technology. I bricked the install three times and had to keep reburning the Jetson OS as the documentation of some seemingly simple tasks is sparse and contradictory.Four stars, minus one star as a warning that you will be messing with hardware and not just jumping into programming.
W**B
thanks so much! love this lil thing
this little thing packs quite a punch. i think it is better then raspi
M**R
A definite improvement
The Jetson Orin Nano is much, much faster than the original nano. It's probably comparable to the Jetson Xavier (I have one) but it feels faster and the Jetpack for it works better. Think of it as a Raspberry Pi designed for machine learning. It does consume a decent amount of power, especially when crunching through images. Make sure to add an M.2 memory card (256G or higher) and flash to the M.2 as it runs orders of magnitude faster than the SD card. For beginners, it's just like running Ubuntu on a RPi. If you've never used an SBC like this with linux, you'll be in for a bit of a learning curve.
Trustpilot
5 days ago
1 month ago