NVIDIA Unveils STUNNING Nano Super Computer for Only $249

NVIDIA's Jetson Orin brings powerful AI to robotics and edge devices—fast, efficient, and ready for the future.

Join My Newsletter for Regular AI Updates 👇🏼

My Links 🔗

Media/Sponsorship Inquiries ✅

Chapters:
0:00 Intro
0:21 Jetson's Launch Video
2:19 What is it?
3:19 Sponsor
5:16 Use Cases and Pricing
6:40 Specifications
7:15 Performance
8:05 Outro

[mehdim]

We definitely want that tutorial Matthew !

[GregoryWilnau]

Would LOVE to see a video of you setting it up!

[kevinschmidt]

I think you need to do an entire training course for this super computer.

[LucaMurgia-jb]

I think it's important to stick to stocks that are immune to economic policies. AI stocks that have the potential to power and transform future technologies. It seems AI is the trajectory most companies are taking, including even established FAANG companies. Maybe there are other recommendations?

[haroldasraz]

This tiny computer is fascinating. Please make a video on running 2 or more NVIDIA's Jetson Orin together as one supercomputer.

[desmond-hawkins]

"This tiny supercomputer can run *275 trillion* operations per second (TOPS)" → This is incorrect: the 275 TOPS number is for the Jetson AGX Orin which costs *$2, 000* and certainly not $250. The $250 model is the Jetson Orin Nano which reaches *67 TOPS.* As the NVIDIA page shows, there are 7 Jetson Orin modules in total, with a whole range of performance. For comparison, an RTX 4090 has 16, 384 CUDA cores while this $250 board has 1, 024. It also has "only" 8GB of VRAM, which is an important limiting factor when it comes to LLM. Llama 3.2 should work on it, but maybe not much more. For most people who already have a PC, a gaming GPU makes way more sense. This specialized hardware is mostly interesting for robotics and edge compute, not much else.

[robs]

Yes, sir. Would love to see a tutorial on how to set this computer up. Looking forward to it

[psypher]

Yes, make a tutorial to set it up, elaborate the expansive spectrum of uses cases to built upon this. Thanks very much!

[frankjohannessen]

These are Ampere-GPUs...30-series. And it uses regular LPDDR-memory @ 100GB/s. Jus get a 3060 instead. It will have 50% more memory and be 260% faster.

[spleck]

Some confusion here.. the tiny computer is the jetson nano.. the super jetson nano is capable of 67 TOPS… the larger more expensive jetson hardware (not the nano) can get up to 275 TOPS. The tiny computer can NOT get 275 TOPS.

[jksoftware]

The amount of ram is pitiful 8GB is NOT ENOUGH should be at least 16gb of ram. I would not even mind if it cost a bit more if we got 16gb of ram.

[TheStickyBusiness]

1:52 I remember the time I had something with that size on my pocket, it was called WALKMAN! The world has changed just a little bit LOL

[ThaiNeuralNerd]

Yes, definitely make a video on setup!

[TheeBadTake]

I mean, We need to know how to chain together. A tutorial on that would be cool. And we need to know how many we can chain to gether. Can we do it up to 80 vram? What is doable and what isnt. The limitations.

[donniejohn]

Excellent and descriptive video. A video with instructions of how to set it up and use this would be AWESOME!!

[RobotechII]

You're not plugging this into a car to have it autonomously drive, you're vastly underestimating the hardware requirements. Also with just 8gb of RAM this is just a toy.

[TomislawDalic]

We need a tutorial how to set it up I Just placed my order.

[RetiredEE]

I will wear mine like Twiki, around my neck. BEDEBEDEBEDE pretty cool Buck, BEDEBEDEBEDE

[chriswatts]

Great device - Agents local at home - multimedia - control of smart home - think about old people having those at home asking them for question to organize stuff around the house, everyone can afford it. Local AI is the future, I am now running phi4 14b Model on my local Unity Game and the quality of this LLM is amazing on a medium gaming pc.

[mariuscg]

First 20 seconds into the video convinced me to get one 😁
Anyone else felt the same? 🤔