Nvidia was the first to announce the desktop AI solution called DGX Spark but AMD was the first to market with the Strix Halo. I was really excited when I heard about the DGX Spark and 128G usable vram, it wasn't until the AMD launched out of nowhere did I realize how disappointing these devices are. The DGX Spark was expected to be about 10-15% faster than the Strix Halo due to the faster ram, but reality is far from that.
These devices are using shared ram similar to what Apple does with the mac. So while the memory bandwidth is far higher than typical CPU only solutions, it is still considerably slower than modern GPUs. For example the Strix Halo memory bandwidth is rated at around 253GB/s and the 5090 is 1,792GB/s. The difference in speed explains why these devices are so much slower than pure GPU vram, but having 128G vram allows you to run far larger models.
After looking at the reviews for the DGX Spark, it's actually laughable how bad it is.
This is the same model I run on my Strix Halo, the Spark gets 94.67 tokens/sec for prompt processing and 11.66 tokens/sec for token generation. My current speeds right now without my nvidia 3090 hooked up is 793.50 tokens/sec prompt processing and 45.88 tokens/sec for token generation. Over 800% faster prompt processing and 400% faster token generation. The funny thing, is the Strix Halo is half the price of the Nvidia DGX Spark.
Current speeds with my Strix Halo
Current speeds with my Strix Halo & Nvidia 3090 hooked up via oculink
The speeds of the Spark look so bad I can't imagine it is really usable for anything. Unless they get those speeds up 200-400% I can't see it being usable even for testing.
My Frankenstein Strix Halo w/ Nvidia 3090.
50 tokens/sec is very usable and sufficient for testing and even some production use. I mostly use my Strix Halo for testing and experimenting, most of my production work is done through cloud API for performance reasons. When I can get my new project proof of concept working and show it is profitable, I will build a private AI solution at a much larger scale.
Nvidia images are pulled from Nvidia Website
But sHaReHoLdEr VaLuE!
My little minisforum box should arrive today. While I won't be using it for AI, I am looking forward to the opportunity to learn proxmox and get some LXC running.
Okay... but as someone who was at Nvidia Headquarters today I feel like I have to play Devil's Advocate here just a little 😁
The AMD Strix doesn't have CUDA support which can be a deal breaker to A LOT of developers. And the Spark's 128GB RAM is available to both the CPU and GPU due to the Grace Blackwell architecture. I believe the Spark can handle up to 200B parameter models as well where the Strix can do up to 70B parameter FP16 models. Not to mention if you have 2 Sparks and
Now that being said, the "Founders Edition" of the Spark is $4,000 and the Strix is in the $2,000 range I think.
But other OEM's like ASUS are selling the Spark for around $3,000 so mileage may vary.
I paid $1800 for my Strix and I run a 120b q8 model at 50 tokens/sec. I have run Qwen3 235B as well.
Cuda is becoming less of a deal breaker with rocm improving rapidly.
I don’t take the Strix or the Spark seriously, in my opinion they are both toys.
well yeah, they are toys compared to Enterprise infrastructure. But both of those run on normal 120V power outlets so they can be used in everyday homes.
A DGX runs n 240V C19/C20 cables so not really an option for 'normal' people.
So get 2 Spark devices connected over their ConnectX-7 ports and you can run any 'consumer-grade' model.
And CUEA being less of a deal breaker is true but moving from 99% market share to 94% is less as well, doesn't mean that they all AI Enterprise developers still utilize CUDA :)
But enough Devil's Advocate, The spark is cool and is a super efficient tool to run consumer AI models but so is the AMD Strix.
Won't you let me work on hive? You blacklisted me, which is why my sixth day's post was downvoted, even though I'm a verified user of hivewatcher.
With respect good day @themarkymark
May I know why you blacklisted me as I would like to appeal about it.
Thank you.
😍
I would like to play with these toys sometime.
Nice. looking forward to your new solution..
Are you human?
No, I am an Alien.
So it seems.
Hi @themarkymark . Unfortunately, my profile is on your blacklist. All my recent original content rewards are being burned and downvoted by user @buildawhale automatically.
I am a new user in Hive platforms and I am not familiar with the details of this issue. What should I do to be removed from your blacklist?
What is the solution?
Maybe you should have thought about the consequences too, when you decided to abuse hive every way you could.
And you're not new, you registered two years ago.
Hi @erikah
The content that is automatically downvoted these days is all original and produced by me. Please check my new content and tell me what the problem is? I am willing to make changes to the structure of my content to get off the blacklist.
Is there a solution to get off this blacklist?
Have you read my comment at all?
Yes, I read your comment completely. Is it no longer possible for me to be active on Hive? Is there any hope that I can be removed from the blacklist?
No one can stop you from being active.
Being blacklisted has hindered my activity, because without income from content production, I have no motivation to work on Hive.
Yeah, better spend your HIVE while they're still worth more than BLURT! You may have a couple weeks... hahahah! Your downvote power is still plenty to keep nuking my posts and comments, no doubt, but that's about all you're good for at this point. Your account value is still enough to get yourself a trailer and a freezer full of TV dinners, Skidmarky. Quickly, because it drops every hour. HIVE is rotating into BLURT nonstop over the past 9+ months. Quick, to the used trailer dealership! Your retirement awaits! LOL (truly)
Seen it.
Here's something fresh though:
Yet my portfolio looks like this. Go figure.
spam and scam!