YouTube Instagram TikTok How it works FAQ

The fastest way to turn talking videos into clean, searchable text. Free, private and no account required.

About

Built by Rishav Raj with one goal: free transcripts for everyone.

rishav@yttotranscript.com

Transcribe

YouTube to text
YouTube with timestamps
Instagram Reels
TikTok videos

Learn

How it works
FAQ
YouTube transcripts guide

More

Chrome extension
Contact
Privacy policy
Terms of service

© 2026 YTtoTranscript. Made for creators & researchers.

Not affiliated with YouTube, Instagram or TikTok. Respect creators’ copyright.

This AI Supercomputer can fit on your desk... — Transcript · YTtoTranscript

Home/Transcripts/YouTube

YouTube Transcript

This AI Supercomputer can fit on your desk...

NetworkChuck · 5,080 words · 25 min read · EN-ORIG

Watch on YouTube

Share X LinkedIn WhatsApp

Below is the complete, readable transcript of This AI Supercomputer can fit on your desk... by NetworkChuck on YouTube. Read the full text, copy any part you need, or generate a transcript for any video with our free tool.

Nvidia sent me this and I can finally talk about it. This AI supercomputer fits in the palm of my hand and it runs AI models my dual 4D90s can't. This is a whole new category of device, an AI server you can actually afford. Now, I think this might be the device we've been waiting for. Powerful local AI that

doesn't suck. I'm excited to try this and show it to you cuz it might change everything. So, in this video, we're diving into the specs, seeing if it can defeat and replace my AI server, Terry, and discover what it can actually do with real tools like N Comfy UI, open web UI. Get your coffee ready. Let's go.

So, here's what Nvidia sent me. An intense looking box. And inside is the NVIDIA DGX Spark. Dude, I'm holding an AI supercomput in my hand. And here's what's kind of crazy. This is the original DGX1, the server that kickstarted the AI revolution. Jensen delivered this server to Sam Alman to get chat GBT started. Now look at this.

Compared to Spark, which is not much bigger than my coffee cup or phone. Look how far we've come. Okay, cool. It's small. What are the specs? What's it packing? For the brains, we have a GB10 Grace Blackwell superchip, a 20 core ARM processor. It has a Blackwell GPU with one pedal flop of AI compute. One

pedlop. But the memory, it has 128 GB of unified memory. LP DDR5X. It's got a 10 gig Ethernet port. And then this fun rectangle. We'll talk more about that later. This can run up to 200 billion parameter models. The cost, it's about 4K. Is it worth it? We'll find out. But all these specs, what do they mean?

Like, do they mean that this thing can beat Terry? My dual 4090 AI server that cost over $5,000? Let's find out. And by the way, I think it needs a name. We're going to name him Larry. Can Larry beat Terry? Okay, we got Larry on the left and Terry on the right. Let's load up our first model.

Transcribe another video

Paste any YouTube, Instagram or TikTok link to get a free transcript.

Free · No sign-up · Unlimited

Add to Chrome — transcribe in one click

We'll do a small one, the Quinn 38B. Load it up. Prompts ready, set, go. Huh? Uh, Terry is awesome. And Larry, you good, dude? Terry won. So, he had 132 tokens per second and Larry's, the DGX Spark, had 36. I kind of expected it to be faster. Let's try a bigger model. Maybe that's where it shines. Let's try

Llama 3.3 70 billion parameters. We'll load it up and let's try something more technical. Ready, set, go. Whoa, this is kind of embarrassing. >> Hey, >> um, Alex interrupted me during the recording with some urgent news, so I'm going to stop here for now. Okay, so we just had a meeting with Nvidia because

this confused me. Terry beat Larry by a long shot, which is frustrating because I had this whole script written about this AI supercomputer that defeats Terry, but that's not the case. So, me and Alex, my producer, we sat down with Nvidia and said, "What the heck, guys? We're running these AI models on Larry,

and Terry's kicking his butt." And they asked us what models. We told them, and they were like, "Yeah, no duh. Of course, your dual 49ers are going to defeat Larry." And I'm like, "What do you mean? This is supposed to be an AI supercomput. It's supposed to be the best." And then they told me this three

things that actually make this thing kind of awesome. And it's not what I expected, especially the third one. I never even heard of that. Now, before we get started, just know like this thing performs well with LM. I just cannot beat Terry, which Terry is insane. I'm learning that now. I have new respect

for Terry. But one thing Larry is going to be better at every single time is running more stuff. Let's talk about Terry and Larry real quick. And I'm drawing on the very example we're about to talk about. Terry has two Nvidia 4090s that each have 24 GB of VRAM. So Terry's got 48 gigs of VRAM. But then we

look at Larry. Larry has 128 GB of unified memory. What does that mean? It means that memory, that RAM is shared between the entire system, between the CPU and the GPU. Meaning the GPU can use 128 GB of RAM. Right now I have a multi LLM system running. There's all the containers running right now. This demo

was running GBT OSS 12B, Deep See Coder 6.7B, and Quinn 3 embedding 4B. Yeah, a multi- aent system, three models. Right now, it's using 89 gigs. They said it would use 120 gigs, the entire almost the entire system. But I point that out because that's just something Terry can't do. Terry can run fast. He's a

sprinter, but he can't do a lot. Can't do long distance. When you're wanting to do multi- aent frameworks locally, Larry shines. You might be thinking, well, hold on, Terry. He's got system memory, right? Like, yeah, we do. Terry's got 128 gigs of RAM of system RAM. But these GPUs can't really use that. The bus they

have to take too slow. When you're talking about AI, it's all about the RAM that's immediately available to the GPU natively. Okay, Larry has more GPU memory. He can do more things, run bigger models. Let's test image generation. They said it's actually really good at image generation, and it might be Terry. Let's see. We've seen

Terry's pretty strong. I have my doubts. Now, keep in mind this is probably going to be rigged. I'm using an example that Nvidia gave me to show off the power of this device. Let's make it happen. All right, Terry on the left, Larry on the right. We got Comfy UI spun up. We'll do

a basic image generation pipeline. I'm going to change the image size to the recommended size they well recommended. And by they, I mean Nvidia. Make the image box bigger down here or up here. And we'll run that basic pipeline. So, we'll go on uh Larry first. Actually, we'll do um let's give it a lot of

images like 20. Uh no, not 32. We'll give it 20 images to make. And if you've never done local AI image generation, it's wicked fast, maybe. Ready? Let's go. Larry first. Go. Go. Okay, things are happening. Loading the model, creating stuff. So, Terry's already gone crazy. Larry's starting now. I can hear him spinning. He's getting hot, dude. A

bit slower, not faster. Now, you can see on the right here on our other screen, it looks like Terry is only configured to use one GPU right now. Terry's done. Larry's like, "I'll get back to you." So, it looks like we have 11 iterations per second for Terry and roughly one iteration per second on Larry. Now, I

think we're all realizing now at this point that comparing Larry to Terry is not apples to apples. It's apples to insanely powerful gaming machine I built specifically for AI. So, let's get real. This thing can fit in my backpack. It's ridiculously small and for its size, it's very powerful. The fact that you

can even do what I'm doing right now, generating images is crazy. And it has okay inference. And by inference, I mean when you're chatting with it, that's what inference means in AI. When you're actually getting results after you've trained it. Now, let's do a fun image. This is kind of boring. I said a pug sipping coffee. Oh, it's

cute. Oh, that's cursed. These are just fun to look at. But what's cool is like this is still all yours. Like it's put it in your pocket if you're wearing Jeno jeans. And you can generate stuff like this nano banana wherever you go. Like that's that's awesome. And the images are I mean if

you if you really dialed this in like if you drained it yourself it would look cool. This thing is actually getting I can hear the fans. Um it's uh it's getting toasty. I could overe an egg on this right now. I'm exaggerating but it's it's good. It's getting there. And the steel wool they have on the sides

that's actually still cool. I don't know what that is exactly but I know it's probably just to look cool but also help keep it cool. Either way I think the design is actually pretty neat. Oh, that actually hurt when I put my You know what? Need I say anymore? Coffee cup warmer. But seriously, I'm running AI and

keeping my coffee hot. Nvidia, you did it. I'm not kidding. My coffee is getting kind of cold. I'm going to keep it there for a second and generate 40 more images. So, image generation was two. 2.5 is training. Training an LLM to think the way you want it to think. giving it your own data and tailoring it

to your very specific use case. This is where it would actually be better than Terry because training actually takes more VRAM. Let me walk you through an example where they actually gave me a training data set I could play with. I want to stop this image generation. My coffee is getting a little too hot. I'm

just kidding. Terry on the left, Larry on the right. Let's run some training. Now, we're training on a smaller model. It looks like Terry has already loaded all it needs to do and it started training and it's doing roughly one iteration per second. As soon as Larry loads his shards, we'll be able to see

what he does. But dude, Terry's firing on all cylinders here. Okay, I can hear Larry starting to spin up and get crazy. Okay, and he's training. There's our metrics right there. Now, here a higher number is not a good thing. It's taking him 3 seconds per iteration, whereas Terry only takes 1 second for an

iteration. So, Terry is roughly three times faster for training, which Nvidia is like, he might be faster. He could be faster than Terry. Doesn't seem like it's the case. Again, let's keep in mind Terry's only three times faster than this little bitty guy. So, grain of salt there. And then there's another thing we

have to consider here. This is why this device will probably be the best thing for AI developers. This is really the target audience. High inference. It can happen. But this is where it shines. Remember, training takes more memory, more VRAM on that small model. I think it was an 8B. They could both do it. But

if I wanted to train a 7dB model like a Llama 3, Terry just wouldn't be able to load the memory. Like look at this. As Larry is loading this model into his memory, look how much is being used. It's going to keep going up. Okay, so I have no idea how long this is going to

take. So while this is loading, let me show you something I love about the Spark. And why I think this this might be a killer option for a lot of people, they make it easy to use. Now, there are two ways Nvidia gives you to access your Spark easily. First, you can just plug a

keyboard and mouse in a monitor and use this like a stinking computer. When you're using the desktop setup, it's running Ubuntu where they call it DGXO OS. Just their version of Ubuntu with all the drivers and stuff you need. I'm not going to try and run a different OS on this thing. That's terrifying. I've

spent all day troubleshooting. The second way, they have an application called Nvidia Sync. I want to download that right now. And what this does is simplify getting access to this and using tools for everyone. You can see down here I have the option to add a device. Once I launch it, it will detect

the apps I have. It can integrate with a cursor or VS Code. I have both. Then I connect to it. And what this is doing in the background is making SSH access super simple. Copying over your SSH key to the Spark and it just connects for you. It'll add my device. Get started. Nice

little graphic they have there. I get a nice dashboard I can log into. I can jump right into Cursor or VS Code, launch a terminal from here. So that make it really easy for someone just to come in with their laptop and go, I want to access this thing and do stuff. And

it connects you. Now, speaking of connecting you, if you're going to have your AI local, like here on my desk, you want to be able to access it everywhere, everywhere you go, but you don't want to necessarily have to take it with you. Leave this on your desk at home when you're at Starbucks or whatever. You

want to be able to access this and use it, run your AI workloads all the time, just like you would in the cloud. In my opinion, the best way to do that is with Twing. Twate is a sponsor of this video and an amazing partner with my channel. Oh, look at that go. And this system

memory is not accurate. That's not how much we have available right now. Oh, time to heat up my coffee. Twinate is a zero trust remote access solution. It's my favorite because it's free for up to five users. So, unless you're running a company or have a super large family, you should be fine. And it's insanely

easy to set up. Like seriously, all you got to do is go to twing.com/networkshuck. Check the link in the description. Create your first network in the cloud and then deploy your first connector. And when we're talking about the Spark, we're just going to log in and paste in one line of config. Like seriously,

watch this. I'll launch my terminal with the sync app. Paste this command in. Twin Gigate gave me this and I'm connected. So now, no matter where I go, I can access securely. It's like VPN, but way better, more secure. You're not opening up any ports in your network. You don't have to be a network wizard to

make Twin Gate work. Dude, this thing's cooking out. They have an app for pretty much every device, iPhone, Android, your Mac, Windows machine, whatever it is. And you're getting enterprisegrade security cuz companies pay and use for this, but you're getting it for free. Try it out right now because they are awesome. I legit use them personally and

for my business. and they help make videos like this possible. They're one of my main sponsors. They're awesome. Anyways, training's started and this thing's cooking. So stinking hot. Let's stop that now because I think my coffee is about to boil. Take a break, bud. You've been doing good. So again, this right here,

training, fine-tuning, it shines there mainly because it has more VRAM and it's a great option for developers who don't want to have to rent a cloud GPU to train their stuff, which I had to do that when I was training my voice for Terry. I rented some cloud GPUs. They're like 30 bucks an hour. Gosh, don't

forget to turn that off. If you have this sitting on your desk, it might take a bit longer than a cloud GPU. Yeah, but it can do it. And that's the key thing. It can actually load and train the models. It's hardware is built to train AI models. That's awesome. And it's so

tiny. And number three, FP4. With AI models, you can quantize them and make them smaller so they're easier to run on smaller devices like this guy here. If you're running a model at FP16, you need a lot of VRAM, but you're getting some of the best quality possible. But we can quantize the model down to FP8 or FP4.

The quality does degrade as we quantize it, but it makes it possible to run on smaller devices. Now, why am I pointing this out? It's because this guy is built to run FP4 like a champ. In fact, they say that it can run FP4 at pretty dang close to FP8 quality with models that

have been specially made for it. And they actually provide an entire tutorial on how to do NVMP4 quantization. So for example, this one takes the Deepseek R1 distill llama 8B and uses the model optimizer using two levels of scaling to keep accuracy while using fewer bits. So it keeps accuracy close to FP8, usually

less than 1% loss, which that's pretty cool. But the biggest thing is they have hardware specifically built to run FP4. Now what does that mean? Well, think about a consumer GPU like Terry. Terry, he can run FP4, but not necessarily in hardware. You see, Terry has to convert FP4 in software. He has to think about

it before he can actually run it. Larry, on the other hand, has special hardware programmed to run FP4. It's all happening in hardware super fast. And this makes Larry great for things like speculative decoding, which is a new term I got to learn during this video. It's actually kind of a cool concept.

And here's what it does. So, while Larry, he's not necessarily great for fast inference, speculative decoding makes it to where he can be super fast. And this is also what makes him unique compared to other local AI hosting options. And here's how it does that. Speculative decoding speeds up text generation by using a small fast model

to draft several tokens ahead, then having a larger model quickly verify or adjust them. So, the big model doesn't have to do all the work. The smaller model is doing that, but he makes sure the output quality is good. reducing latency. Now, to do that, we're essentially running two models at the same time, requiring more VRAM, which

consumer GPUs just couldn't do. Let's test this out. Okay, I've got the models loaded up. I mean, look at this. It's using 77 gigs of VRAM. Let's uh test it out with a query. Explain the benefits of specul that word scaling me. Speculative decoding. Let's watch it have a fit heating up. It's being used processing.

So, what's happening here again? Smaller model is doing the stuff. Bigger model checks it. That was actually pretty stinking fast using 70B. Does it give me any token statistics? No. It fell fast though. Okay, Spark has its advantages. Okay, Larry, he's got some things going for him. He's not the fastest guy on the

team, but you can put him in any position. Shoot, he can play four positions at one time. The analogy is going off the rails. He can do a lot for how small of a guy he is. But the big question is, should you buy him? Now, the model I have here, it's got 4 TB of

storage. It's a Founders Edition. It cost 4K or $3,999 because marketing. They will have cheaper variants from OEM partners. I think they'll have a two TBTE model for like $3,000. They haven't put the numbers out yet, but that's what I've heard. So, let's compare him to Terry. Terry cost over 5K. Terry's massive.

Like, I had to lift him up into the other room to film some B-roll for him. I'm like, "Oh my gosh, I think I hurt my arm. Actually, I'm also getting old, but my arm hurt this weekend." Terry draws a lot of power. If you're to run Terry for a year, it's going to cost you $ 1,400

bucks. That's how much that's costing me. Terry, the Spark will roughly cost you $315 in a year to run. And that's running 24/7. Oh, I forgot to mention the Spark is 240 watts while Terry is, what do we say, 1100 watts. So, the footprint is certainly smaller. We're not running a data center here. But the

thing is, I don't think Terry's the best comparison for this. There's some newcomers in the market that I think are pretty interesting. I just saw one from Surf the Home, a YouTube channel I love, and it's a Beink device that has the new AMD AI chips in it. This Beink device also has 128 GB of unified memory. So,

they're neck andneck on those specs, but they don't have the Nvidia Blackwell chips that are optimized for FP4. They've got AMD doing whatever AMD is doing. Looking at his performance, the inference is pretty similar to this guy here. The device itself is like a mini PC, the same size, but the cost is

around $2,000. Now again, this is not apples to apples because when you're comparing Nvidia to AMD, Nvidia is way ahead of the game on AI. The AMD AI stuff, it sounds pretty cool, but you have to have things developed for it. You have to have a whole ecosystem around that to use some fun stuff.

Nvidia's already got that. They're way ahead. Now, disclaimer, I've not played with any of these new AMD AI things yet, which is why I'm like not even using technical terms when I'm describing it. I just know they exist. And because I didn't have very much time to make this video about this device, what I can say

right now is Nvidia is the option you want if you want things to work and you don't want to spend so much time getting things set up and troubleshooting. And that's from getting this thing set up. I mean, like literally, I unboxed this and they have instructions to use your phone to connect to its Wi-Fi hotspot and get

it connected to your Wi-Fi. Like it has the ease of use like buying a smart home device. Like I think I had more trouble connecting my light bulb to my home assistant than getting this set up. That's plus 10 points. 10 points to Gryffindor. The NVIDIA sync thing is very cool. It gives developers an easy

way just to boom connect to it. They don't have to be DevOps people. They don't have to be nerds like me, although everyone should be. They don't have to know how to do a home lab. They don't have to build Terry. Terry took a lot of work. So, I can tell NVIDIA put a lot of

work into making this simple. You're kind of getting that Apple experience. And there, that's kind of the way I see it. They're like the Apple of AI right now where Apple is not the AI of anything. Although, hold on. There is one more thing we got to think about. Actually, we got to bring up Apple here

in a moment because this guy's not the only one doing unified memory. Now, what the Spark has going for it is you can add another Spark to it. It has a QSFP port on the back which will give you blazing speeds to another Spark using NCCLG GPU toGPU communication. They're saying you get 200 Gbits per second of

bandwidth. And while the inference speed won't be as fast as on one, you'll be able to do more with two. So, I say all that to get to here, should you buy one? And really, I'm asking the question for myself like would I buy one? Now, first they said it was an AI supercomputer.

I don't think this feels like a supercomput. Maybe a mini supercomput. Maybe that's a better marketing term. I get the marketing thing. This doesn't quite say super to me. It's impressive what it does, especially for the form factor. But for me, $4,000 for a device like this, I would want higher inference speeds for myself. When I thought about

this device before I saw any of the specs, I was hoping like, oh, we're gonna have a device built for us for high inference. So, Terry in there, great at high inference, but he's only got 48 gigs of RAM. I want a GPU with a ton of VRAM. Forget the gaming. Put the

gaming to the side. I want to do AI. Design something for a consumer to do that. This, I don't think, is really meant for a consumer. At least not for me wanting high inference. Now, on the other hand, if you're a developer and your main job is like developing AI, you're fine-tuning, you're doing all

that fun data science stuff, which I don't normally do every day, that's not my day-to-day, this might be the device for you because you don't have to rent something in the cloud. This device can pay for itself over time. If you're renting a GPU in the cloud for 30 bucks, it's not going to give you the same

performance as the cloud, but it can do the same stuff as what you can in the cloud, whereas before that really wasn't possible. So having this and just being able to connect it to your laptop over the network and it just is so tiny and small and just sits there, that's pretty cool. So if I'm fine-tuning every day, I

would think about getting this. But if I'm running O Lama open web UI, Comfy UI, doing some crazy high inference tasks, I want more speed. Terry still wins, but I cannot wait for the day where someone, I don't care who gives it to us, gives us a device like this that can run the biggest and baddest models

at cloud speeds. Or at least just give me half that speed. Just give me something. Now, I'm curious though, and I have not tried this yet. I've not attempted this yet. I wonder how this will do against a Mac. Speaking of apples to apples, Macs have unified memory. Now, you saw me cluster five

Macs together. I right now actually have it's attached to stuff. This is a Mac that Apple sent me. It's a Mac Studio M3 fully maxed out. It's got 512 GB of unified memory. I wonder how this would do against this guy. I think I'll do another video on this. Anyways, that's all I got. I don't normally do reviews,

but this is kind of like something I've been waiting for. It's been on my wish list, and I'm so glad Nvidia sent this to me. They had no control over this video. They did not see this video before. They just sent this to me and said, "Hey, please look at it." They were very gracious in giving us their

time to help us learn this device and what it can do. But they had no input into this. So, what do you think? Is this the groundbreaking device we've been waiting for, or is it like meh? And I mean, if you're a developer, like, does this get you excited? Like, oh my gosh, finally I can finetune on my desk.

That's That's a cool idea. Let me know below. I want to know your thoughts. Anyways, that's all I got. I will catch you guys next time. Hey, I was just watching the review of this video and I realized, oh my gosh, I forgot to pray at the end. I'm trying to start doing

that now. And if you're like, what are you talking about, Chuck? Um, I'm starting a new thing at the end of my videos where I just want to pray for you guys, my audience. Um, you're the reason I'm here and I want to see you succeed. I want you to have an amazing career.

here. I want you to have an amazing life. I want to pray for your families. Uh now, why am I doing that? I'm a believer. I believe in Jesus Christ. And um he's the reason I'm here doing what I do. So, I'm not sure where you're at and your belief. I'm sure I I know my

audience has a wide breath of beliefs. Uh but I would love just to pray for you. Um no pressure. If you want to end the video now, that's totally cool. If you want to hang out and just hear a prayer, hey, I would love that. So, I'm going to pray for you right now. It is

weird, I know, but I'm going to do it anyway cuz let's go. God, I uh thank you for the person watching this video. Um, I pray right now that through this computer screen, over the internet, through the bits and bites that I believe you control and you have power over, I pray over this person that they would be full

of energy and excitement for technology and that um, first give them wisdom on whether or not they should buy this device, but also bless them in their career. Uh, they are learning these things because they're excited about tech. And I pray that you would take these skills and this interest and this curiosity and turn it

into um positions and and uh influence and blessing for the people in their lives. Lord, uh bless their families and be with their their friends and their co-workers. Allow them to be a light in their life. And uh I ask that just this video they're watching now would encourage them to do some amazing things in their life and

their career. And ultimately I pray that they would find their meaning, their their identity, their the reason for being in you, Lord. Because at the end of the day, this stuff is super fun, of course, and we can obsess over it, but there's more to life than this. So, I pray they find

that. It's in Jesus name I pray. Amen. All right. Thanks, guys. I'll catch y'all later.