HP ZGX Fury Is Now Orderable: GB300 Superchip, 748GB Unified Memory

rrbanffy about 3 hours ago 42 commentsRead Article on storagereview.com

⚡ Community Insights

Discussion Sentiment

59% Positive

Analyzed from 1104 words in the discussion.

Discussion (42 Comments)Read Original on HackerNews

fc417fc802•about 2 hours ago

> a Kensington slot

I think you might need a bit more than that at this price point ...

alexfoo•about 2 hours ago

At the expected price point it would be nice if it came with a free pied-à-terre in Kensington (https://en.wikipedia.org/wiki/Kensington). Just a small studio apartment, nothing special.

noir_lord•about 1 hour ago

You'd need to spent ~£500K+ to get a studio in Kensington these days that isn't a shoebox.

One listing is 410K for 280 sq/ft coming out at £1464 per square foot, almost exactly 10x the price per sq/ft we paid for our house a few years ago.

So $100K would be £74K which would get you ~50 sq/ft.

yread•32 minutes ago

A square (or cubic?) foot would be enough to house it

Retr0id•about 1 hour ago

A kensington lock in this context is like a sign that says "do not move", which is still kinda useful

fortran77•23 minutes ago

I have a $50,000 Tektronix 'scope on my bench that's Secured with a kensington lock. I am in a small office in a building I own and I rent out some extra space to another 3 person engineering company. One weekend they tried to remove my 'scope from the bench because they had something "important" to work on. They quickly discovered the lock. (The whole thing was caught on camera.)

They weren't trying to steal it, they just wanted to bring it over to their side. But the lock did its job! This is the perfect situation for a Kensington lock.

I yelled at them the next day telling them if they need a Series 5 'scope they could go rent or buy one.

pritambarhate•about 2 hours ago

Looks like multiple vendors are seeling these:

https://www.gigabyte.com/in/Enterprise/Tower-Server/W775-V10...

https://www.msi.com/Landing/NVIDIA-DGX-STATION

theplumber•about 1 hour ago

Someone should edit the title to make it clear it only has 252GB of “AI” memory

edg5000•34 minutes ago

Agree, the CPU memory is about 400GB/s vs. Apple M5 Ultra at 1.2TB/s. But the M5 only has that, not the 7TB/s portion. So this box could* still be faster when using the full 748GB if both RAM types can be used without the slower part bogging everything down. *That comes down to implementation. Maybe somebody can chime in on this.

dsrtslnd23•about 2 hours ago

252GB of HBM3e at 100k vs. a multi A6000 96GB setup. GB300 seem expensive in comparison at ~$100k. Am I missing something?

_diyar•about 2 hours ago

Without looking it up and doing the math, I bet GB300 has higher Tflops and memory bandwidth, especially when used with e.g. NVFP4.

hgoel•about 2 hours ago

Plus lower peak power draw

rbanffy•about 1 hour ago

How long until the higher power draw nullifies the higher acquisition price of the GB300 machine?

cmrdporcupine•about 1 hour ago

There's a lot more going on here because the host machine has a boatload (496GB) of expensive LPDDR5x (which is stupidly expensive) that can also be used as unified (but slower) memory to the GPU, 72 ARM64 cores, stupid fast NVlink/QSFP networking, the PSU to support all that etc. etc.

Basically it's the same as a tray in a GB300 NVL72, but in workstation/desktop form. Niche would be AI researchers.

They will... not sell a lot of these. But what a beast.

I am too lazy to price out 496GB of DDR5 but, um, mostly because it is terrifying to see what today's prices look like.

You can't build such a machine out yourself but if you could I suspect the price point would come out about the same.

rbanffy•about 1 hour ago

> You can't build such a machine out yourself but if you could I suspect the price point would come out about the same.

That's kind of the nature of capitalism and price elasticity - the manufacture price only limited the minimum sale price, and sale price usually reflects how much is the market willing to pay for the good.

Where you might save a lot of money is on building something that's very targeted to your needs that matches them better than a GB300 workstation, for a lower price.

cmrdporcupine•about 1 hour ago

But the point of such a machine generally is to have the equivalent of a GB300 NVL72 tray on your desk. It's so that you can do the work that belongs in a production DC eventually. Or at least that's now NVIDIA would like you to use it.

You could build out a complicated multi GPU setup of your own, but the work you do on inference tuning for your kernels etc would not necessarily translate to the real world.

But yes, if you just want to run GLM 5.3 on your own machine, that's a whole other story.

LargoLasskhyfv•about 2 hours ago

HP’s spec sheet fills in details the platform announcements skipped. The CPU memory is four 128GB SOCAMM modules delivering 396GB/s, and the Grace CPU is soldered to the host processor module rather than socketed. The two pools add up to the 748GB coherent space that lets the GPU address CPU memory directly, which is what makes trillion-parameter inference and fine-tuning of models in the 100 billion parameter class possible on a single box. HP’s footnote on those model sizes is that the harness quantizes at FP4.

Retr0id•about 2 hours ago

How many arms and legs does one of these cost?

shmoil•about 2 hours ago

3.14 kidneys.

dyzone•about 2 hours ago

But can it run crysis?

jareklupinski•about 2 hours ago

if not yet then it may be achievable:

https://www.guru3d.com/story/nvidia-dgx-spark-achieves-175-f...

kstrauser•22 minutes ago

Can you imagine a Beowulf cluster of these?

einpoklum•about 2 hours ago

Can I get 32 GB of RAM for a sane price instead?

self_awareness•about 2 hours ago

I guess I'm too poor to even know the price

wolttam•about 2 hours ago

MSI’s DGX Station (what this is) was listed for $99K

chedabob•about 2 hours ago

Dell's equivalent starts at £180k.

NKosmatos•about 1 hour ago

These are for billionaires/multi millionaires/cryptobros/stupidly rich people who can afford such “toys”. I’d really love to see a geek/tech freak/gadget lover/IT/homelab billionaire buying large number of things we mere mortals can’t afford, but only dream of, and then he blogs about them ;-)

fortran77•20 minutes ago

Since I'm a "retro computing" guy, I look forward to buying one of these on eBay or at a Vintage Computing Fair for a few hundred bucks 5 years from now.

Gigachad•39 minutes ago

I’m gonna bet in 5 years the price will be in range for the average tech bro to get their hands on one.

It just doesn’t make sense to buy this stuff at peak prices.

theplumber•about 2 hours ago

>> 252GB of HBM3e at 7.1TB/s,

So it has only 252GB of actual ”AI” memory making it “useless”/toy for actual real world AI workloads(I.e it can’t replace something like opus 5)

theplumber•about 2 hours ago

I find it just misleading by advertising 700GB RAM as AI headline. I could plug a 32GB GPU to my 1.5TB ram server and call it “AI station with 1.5TB+ RAM” just so that you find it actually useless compared to the headline

kees99•about 2 hours ago

Should work just fine for MoE models where active set fits into 252GB.

theplumber•about 2 hours ago

Can’t you do that already more or less with a Mac Studio with 256 or better 512fb of ram?

fc417fc802•about 2 hours ago

Where are you getting 7 TB/s of memory bandwidth?

fc417fc802•about 2 hours ago

I don't know about "useless" (it seems quite useful to me) but I do feel mislead. It's unified memory in the same way that my current dGPU has unified memory. I guess nvlink-c2c probably (?) doesn't introduce a bottleneck but it's still two distinct arenas with very different performance characteristics.

cmrdporcupine•about 2 hours ago

7.1TB/s of HBM is not "useless" -- that's 30 times the memory bandwidth of my DGX Spark -- and nobody is expecting such a machine to run "Opus 5" on its own. For such large models even datacentre GB300 NVL72 are multiple trays linked together via NVlink etc. This machine has QSFP ports and ConnectX for linking up for larger models.

It's a workstation, not a rack. It's for AI researchers. I'd love to have one on (err, under) my desk.

What even is this comment?

cagenut•about 1 hour ago

I'm just barely starting to wrap my head around mapping model sizes and quants to hardware components and constraints.

I don't get what this device is for.

I a million percent understand wanting 252GB-VRAM, that would get me a 280-320B model like glm-5.3 or deepseek-v4-flash, which would be a massive improvement over my gpt-oss:20b 16GB toy. I would gladly pay a grand for this, I would never pay ten grand for this, and it seems to be priced around a hundred grand.

So obviously the customer is commercial not consumer.

Can anyone planning a project around one of these at work share what their workload is shaped like and how they're modeling price/performance?

For instance, I don't get the 512GB of system memory, I'd gladly drop that to 128 to save money. Am I missing something about commercial workloads? Is a 1T parameter model at 20 tok/s more important to your workload than a 300B one at 60? Is it simply a co-dependency of not the model but the other software you're running on the machine thats using/interacting-with/being-driven-by the model?

Whats your napkin math to justify 100k? Actually thats not even really the question, its more like - whats your napkin math to determine between the "dual linked GB10" use case vs this product's use case vs an 8U supermicro with 4 cards use case.

Egg-Man•about 2 hours ago

Imagine a beowolf cluster of these!

varispeed•about 2 hours ago

Furious

What is it with those stupid names?

No price, so of course this is not for the smelly working class.