YHK - yet another hacker news clone

Intel D270 GPU AI Accelerator–Up to 480 GB LPDDR5X

65 points hurricanepootis 4 hours ago 20 comments

hurricanepootis 4 hours ago | parent

Looks like Intel is choosing to title its new crescent island cards with the D prefix despite being Crescent Island.

Kind of disappointed that Intel is (probably) not going to release consumer class GPUs. Intel's driver stack was seriously getting mature—both on Linux and Windows. It's always nice to have a third option available.

oddIdentities 1 hour ago | parent

At least that driver stack will continue to mature?

zakisaad 1 hour ago | parent

On Linux mainly, and almost strictly for compute workloads (not much need to optimize for 3D workloads given the customer base).

bpye 1 hour ago | parent

They're still using Xe based iGPUs, so 3D still matters.

DiabloD3 45 minutes ago | parent

For now. A limited run of Celestials until 2028 when Serpent Lake switches to Nvidia tiles, and a bit longer for the LTS combo (AMD style) IO+GPU die in lower end/embedded products.

Druid is still dead, consumer DGPUs are still, and workstation DGPUs also seems to be dead, and most of the Xe driver team for Windows was laid off, as well as most of the Xe chip design team.

jauntywundrkind 1 hour ago | parent

They originally said it was going to be 120GB but that partners could ship bigger capacities. So much for that!

I do hope this has a price point that makes it somewhat competitive with a Mac! Consumers have had nearly no choices available for mem capacity, and 20 channels of lpddr5 is one way to get that capacity! Go Intel!

bigyabai 1 hour ago | parent

Both this GPU and the Mac are constrained by a lack of GPU compute. There's basically no rack-scale GPUs with 480gb on-die that have a sub-400W compute element. It's going to be incredibly prefill-constrained on denser model inference just like the Apple Silicon iGPUs are.

shusaku 1 hour ago | parent

It seems like there’s a market out there that is just happy to run the models locally, even if generation is slow.

krasin 1 hour ago | parent

This GPU has 1.3 PFLOPS of FP8 compute performance and 1.5 TB/s of memory bandwidth: https://videocardz.com/newz/intel-gpu-d270-is-xe3p-crescent-...

This is almost twice better than RTX 5090. This GPU will not be prefill constrained, I feel.

But I am surprised that they were able to pack so much flops into 300W.

kadoban 1 hour ago | parent

> But I am surprised that they were able to pack so much flops into 300W.

I'm not. When you're doing inference you typically reduce power limits anyway if you're optimizing for efficiency. Even if you don't, it doesn't spike to the max of the card.

My 3090 I power it down to 175W or so for single-digit reductions in performance for like, 60% of the wattage, something like that.

jchw 49 minutes ago | parent

Am I wrong to assume that large MoE models are likely the point anyway? Seems like this card would love DeepSeek V4.1 Flash.

rkagerer 1 hour ago | parent

Can I actually buy this? Should I prefer it over Blackwell?

kadoban 1 hour ago | parent

> Can I actually buy this?

No. Certainly not now, maybe not ever. That is the least consumer-focused product page I've seen today.

legitronics 53 minutes ago | parent

Intel ai gpu division is so aggressively anti “small” consumer. I think it has something to do with low volume and a small sales/distribution network. The data center cards I have from amd and nvidia are grey market at best. I don’t think intel moved enough units to establish alternate channels.

cheeze 38 minutes ago | parent

Serious question, would they bother?

You can work with 10 players that will buy all of them with minimal effort.

samuelknight 22 minutes ago | parent

You can tell by the shape of the board that it's meant to go into a server chassis behind a stack of 80mm blower fans. It's not meant for consumers, but you will be able to buy it used for $200 off ebay in 7 years to put in your home lab.

doublerabbit 51 minutes ago | parent

> Efficient token serving Dense, air-cooled, standard PCIe infrastructure helps maximize tokens per rack and watt, scaling serving capacity and keeping costs in check.

Next the tokens will be asking for tequila and caviar. Bow down to the new token overloads.

arjie 34 minutes ago | parent

Seems incredibly little compute for this. Is it meant to be MoE specific?

porkbellyeee 23 minutes ago | parent

Ai generated no doubt

nekusar 14 minutes ago | parent

Yay more vaporware hardware I get to read about and never see or have a chance to buy.