| ▲ | Intel D270 GPU AI Accelerator–Up to 480 GB LPDDR5X(intel.com) |
| 149 points by hurricanepootis 8 hours ago | 67 comments |
| |
|
| ▲ | K0balt 4 hours ago | parent | next [-] |
| These are going to be so awesome to buy in 5-8 years! Right now I’m running 2x 3090 and 128 gb ram on 3.8 flash-next180b (the quant is 97gb) and it hums at120t/s. It’s really a surprisingly good model for general tasks, and I’m soon to see how it does with more agentic kit. For agentic work it does slow down quite a bit when the context fills up… but what do you want for running a 180b model on consumer hardware? Right now I have it set up as an administrator for our asterisk PBX and radius server, and it does higher level judgment on our cctv footage for notifications to security. It’s been really good so far. Agents are the new UI, everything just works over SSH now. |
| |
| ▲ | sixothree 32 minutes ago | parent | next [-] | | Are you running club-3090 or something else? | | |
| ▲ | K0balt 19 minutes ago | parent [-] | | Flash-Next runs on Strata, version 0.1.42, an inference engine built specifically for Qwen3.8-flash-next |
| |
| ▲ | locknitpicker an hour ago | parent | prev | next [-] | | > (...) it hums at120t/s. It’s really a surprisingly good model for general tasks, and I’m soon to see how it does with more agentic kit. This is exactly why I interpret the aggressive price cutting by OpenAI on their Luna model line as a clear sign they are scared shitless of local models, and how they can trigger a "the king has no clothes" moment for AI companies like OpenAI. | | |
| ▲ | Aurornis 33 minutes ago | parent | next [-] | | > as a clear sign they are scared shitless of local models, The number of people with hardware to run a model like that is very small. It's going to be many years before hardware to run medium size local models is widely available. Running mid-size local models doesn't even register as a factor in pricing decisions right now. It's such a small part of the market and will be for many years, until RAM and other hardware prices come down. | |
| ▲ | vladgur 43 minutes ago | parent | prev [-] | | At cost of power at $.45kwh here and dual 3090 setup easily approaching 1kw per hour at 120 tok/sec, latest Luna is cheaper per million tokens. Your electrical costs are likely less than mine though | | |
| ▲ | K0balt 27 minutes ago | parent | next [-] | | Yeah electric costs are nil on the microgrid but capacity is limited. | |
| ▲ | selicos 22 minutes ago | parent | prev [-] | | I'm working off a 128gb Strix system on mostly hydro and it's worth it for me. Qwen 3.8 27B and Flash Next, Gemma 4 and MOE models. It Keeps my thinking and methods local while moving at a speed I can actually read and think about. It can be annoying when you're running something long and realize there is an issue. But hey, I'm not wasting paid tokens. Reset and try again. I've probably thought of a better way by then too. |
|
| |
| ▲ | x0z 3 hours ago | parent | prev [-] | | > These are going to be so awesome to buy in 5-8 years! Literally my first thought! |
|
|
| ▲ | p0w3n3d an hour ago | parent | prev | next [-] |
| To be honest these ubiquitous AI hardware news look to me more and more like Maybach commercials. Not targeting me |
|
| ▲ | suprjami 4 hours ago | parent | prev | next [-] |
| With an impressive 1.5TB/s RAM bandwidth you'd think they'd advertise that more. Marketing department asleep at the wheel. |
| |
| ▲ | auspiv 3 hours ago | parent | next [-] | | This is a very low number for a server GPU. My V100 from 2017 is 0.9 TB/s. A single B300 has almost 8 TB/s. AMD MI300x from 2023 is 5.3 TB/s Edit: my bad you are saying that this is an impressive number precisely because it is more or less normal RAM, not VRAM | | |
| ▲ | pixelpoet an hour ago | parent | next [-] | | VRAM isn't a type of memory, it's just RAM used for the GPU. So this LPDDR5 is VRAM, just like it can be with my Strix Halo machine. | |
| ▲ | genxy an hour ago | parent | prev [-] | | Its bandwidth is around that of 32 DDR5 DIMMS (50ish GB/s). These boards should have built in NICs but they don't because Intel also wants to sell more servers. |
| |
| ▲ | Aurornis 31 minutes ago | parent | prev | next [-] | | > Marketing department asleep at the wheel. The marketing department doesn't have to lift a finger in this market. They could quietly drop it for sale without a single announcement and it would be backordered for a year. | |
| ▲ | layoric 4 hours ago | parent | prev | next [-] | | Source? Extremely impressive if true | |
| ▲ | jagannathtech 2 hours ago | parent | prev [-] | | These things will fly off the shelves with 0 marketing |
|
|
| ▲ | rkagerer 6 hours ago | parent | prev | next [-] |
| Can I actually buy this? Should I prefer it over Blackwell? |
| |
| ▲ | samuelknight 5 hours ago | parent | next [-] | | 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. | | |
| ▲ | littlecranky67 an hour ago | parent | next [-] | | Wonder if there will be consumer video drivers for these GPUs once the AI hardware shortage is over. Hope to buy a gaming rig one day that doesn't cost a fortune. | |
| ▲ | m463 2 hours ago | parent | prev [-] | | Wonder if today's ram will go up price by then... | | |
| ▲ | manquer 2 hours ago | parent [-] | | It is going up one way or another- the price of money will go down - @5% inflation over 8 years the value of today’s dollar will be 67.7c . |
|
| |
| ▲ | kadoban 6 hours ago | parent | prev [-] | | > 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 5 hours 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 5 hours ago | parent [-] | | Serious question, would they bother? You can work with 10 players that will buy all of them with minimal effort. | | |
| ▲ | derefr 4 hours ago | parent [-] | | What I don't understand is: when you only plan for your product to have 10 customers, why even make a marketing page like this for it? At that point it's essentially the hardware equivalent of consultingware, something you sell to your existing contacts through outbound calls and by shoving ads through the B2B equivalent of a post-consumer sales channel (i.e. proactive outreach by your org's internal champion for that customer, to said customer.) | | |
|
|
|
|
|
| ▲ | ismailmaj 3 hours ago | parent | prev | next [-] |
| 1.5 TB/s 1.3 PFLOPS with no fast multi-GPU, it's a consumer card that pretends to be a server card. It would work great on Qwen3.8-Flash-Next or GLM-5.3 as single user decode only hits a few experts, anything with concurrent users and you'd be sitting for a while. |
| |
| ▲ | minraws 3 hours ago | parent [-] | | That's the point I believe fast local 2-4 user service for cheap on very large models. You have to pretend it's for servers to keep investors happy, it would be banks and similar with in house servers that have to run local large models buying these for experiments and cybersecurity. Likely. |
|
|
| ▲ | ckrapu an hour ago | parent | prev | next [-] |
| Slop and placeholder text on the page, including this one. They should have reviewed their webpage. "What software frameworks are relevant to Intel GPU D270? Intel GPU D270 messaging should reference familiar AI software and serving frameworks such as PyTorch, vLLM, SGLang, and OpenAI Triton, where approved. This helps developers and platform teams understand how the product fits into existing AI workflows." |
| |
| ▲ | airspresso an hour ago | parent [-] | | Noticed this as well! Was looking for details on the software support and this FAQ entry didn't exactly instill confidence... |
|
|
| ▲ | ismailmaj 4 hours ago | parent | prev | next [-] |
| Fun to see the LLMism on the product page: "A, not B" |
| |
|
| ▲ | hannasm 3 hours ago | parent | prev | next [-] |
| Can intel gift me one? The cost of a 480gb ram video card seems preposterous to be even marketing at this point. Intel is going to make a card that costs $1 million dollars.. this is like industrial newsletters bleeding into a public forum > Commercial Scale Pricing: In the industrial data center sector, battery storage systems are priced per kilowatt-hour (kWh) or megawatt-hour (MWh). Industrial battery storage installations typically cost $300,000 to $450,000+ per MWh of capacity depending on software integration, cooling systems, and structural framing. Let's all get excited |
|
| ▲ | hurricanepootis 8 hours ago | parent | prev | next [-] |
| 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. |
| |
| ▲ | ank 3 hours ago | parent | next [-] | | Agreed. I was really rooting for them to deliver that third iteration to consumers, and retain them as a competitive option in the low to mid range. Pretty sad to see. | |
| ▲ | boredatoms 4 hours ago | parent | prev | next [-] | | Its wild to me that intel isnt trying significantly harder on gpus Theres so much money to be made | | |
| ▲ | ThrowawayR2 4 hours ago | parent [-] | | Why make consumer margins on consumer GPUs when they could be making enterprise margins on enterprise GPUs? | | |
| ▲ | jandrese 42 minutes ago | parent | next [-] | | One word: Volume. You can make a nice profit off of the enterprise space, but the big winners are the guys who put the work into servicing the consumer market. | |
| ▲ | boredatoms 3 hours ago | parent | prev [-] | | I mean, why not both | | |
| ▲ | ThrowawayR2 3 hours ago | parent [-] | | "Both" requires more engineering staff on payroll, more wafers to fab/dice/package/test, more boards to manufacture, more inventory to manage, among other things. If their math says it isn't worth it (granted that they don't always get it right), then they don't do it. | | |
| ▲ | zargon an hour ago | parent | next [-] | | "Both" requires allocating limited die capacity to products that have over an order of magnitude less margin. | |
| ▲ | locknitpicker an hour ago | parent | prev [-] | | > "Both" requires more engineering staff on payroll, more wafers to fab/dice/package/test, more boards to manufacture, more inventory to manage, among other things. Aren't you describing how a business operates? I mean, doesn't Intel already hire people for those tasks? Unless you are worried about a specific bottleneck, increasing headcount and production output is what businesses do. |
|
|
|
| |
| ▲ | oddIdentities 6 hours ago | parent | prev [-] | | At least that driver stack will continue to mature? | | |
| ▲ | zakisaad 6 hours ago | parent [-] | | On Linux mainly, and almost strictly for compute workloads (not much need to optimize for 3D workloads given the customer base). | | |
| ▲ | bpye 6 hours ago | parent [-] | | They're still using Xe based iGPUs, so 3D still matters. | | |
| ▲ | DiabloD3 5 hours 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. |
|
|
|
|
|
| ▲ | arjie 5 hours ago | parent | prev | next [-] |
| Seems incredibly little compute for this. Is it meant to be MoE specific? |
|
| ▲ | nunzioraciti 3 hours ago | parent | prev | next [-] |
| How much is it expected to cost? |
| |
|
| ▲ | jauntywundrkind 6 hours ago | parent | prev | next [-] |
| 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 6 hours 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. | | |
| ▲ | krasin 6 hours ago | parent | next [-] | | 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 6 hours 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. |
| |
| ▲ | shusaku 6 hours ago | parent | prev | next [-] | | It seems like there’s a market out there that is just happy to run the models locally, even if generation is slow. | |
| ▲ | jchw 5 hours ago | parent | prev [-] | | Am I wrong to assume that large MoE models are likely the point anyway? Seems like this card would love DeepSeek V4.1 Flash. |
|
|
|
| ▲ | aboardRat4 4 hours ago | parent | prev | next [-] |
| How many fps in Cyberpunk 2077? |
| |
|
| ▲ | porkbellyeee 5 hours ago | parent | prev | next [-] |
| Ai generated no doubt |
|
| ▲ | doublerabbit 5 hours ago | parent | prev | next [-] |
| > 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. |
|
| ▲ | nekusar 5 hours ago | parent | prev | next [-] |
| Yay more vaporware hardware I get to read about and never see or have a chance to buy. |
| |
| ▲ | Gigachad 4 hours ago | parent [-] | | This stuff you usually buy second hand in 6 years when the data centers get rid of them. |
|
|
| ▲ | gravypod 2 hours ago | parent | prev | next [-] |
| [dead] |
|
| ▲ | typon 2 hours ago | parent | prev [-] |
| [dead] |