CONFIRMED: Intel announced the name and specifications on 12 October 2026 at the OCP Global Summit. Performance figures are COMPANY CLAIMS. The lack of a launch date is REPORTED by ServeTheHome.
At the Open Compute Project (OCP) Global Summit, Intel “shared new technical details on the Intel GPU D-series, formerly code-named Crescent Island, introduced new Intel Xeon-based rack designs and highlighted open software and ecosystem innovations” [1]. Intel’s product page names the first card the Intel GPU D270 [2].
The D-series is a graphics processor (GPU) built for AI inference, meaning running trained AI models to answer requests, rather than training them.
The specifications
Intel says: “Built on Intel’s latest Xe3P architecture, the GPU combines up to 480 GB of LPDDR5X memory, 1.5 TB/s of memory bandwidth and 1.3 petaflops of FP8 compute within a 350-watt power envelope” [1].
The 480GB figure is the maximum. A footnote in Intel’s announcement says: “Intel branded PCIe card has 160GB LPDDR5x, design enables partners to build ODM branded cards with flexible options up to 480GB memory” [1]. StorageReview reports the same split [3].
The product page lists 32 Xe3P cores and 256 XMX matrix engines, and describes the card as “Standard PCIe 5.0” and “350W air-cooled” [2].
PCIe is the standard slot used to plug cards into ordinary servers. Air-cooled means it does not need liquid cooling.
Intel says the card’s “standard PCIe form factor, air-cooled design” lets customers “scale inference without specialized rack or cooling infrastructure” [1]. It says the D-series “supports models with up to 300 billion parameters on a single card” [1].
Availability
Intel says customer sampling is underway [1]. ServeTheHome reports that Intel “has not yet announced a launch date for the cards” [4]. Intel did not give a price.
New Xeon racks
Intel also showed “new Xeon-based rack designs developed with ecosystem partners”, many using the OCP Open Rack v3 standard. It says “select Xeon 6+ configurations scale beyond 46,000 cores per rack at 133.45 kW total rack power” [1].
Sources
- Intel Newsroom, “Intel Accelerates Open Infrastructure for the Agentic AI Era”, 12 October 2026. https://www.intel.com/content/www/us/en/newsroom/news/artificial-intelligence/intel-accelerates-open-infrastructure-agentic-ai-era.html
- Intel, “Intel GPU D270 | Inference-Optimized Data Center GPU” (product page). https://www.intel.com/content/www/us/en/products/details/discrete-gpus/data-center-gpu/d-series.html
- StorageReview, “Intel GPU D-Series Packs 480GB LPDDR5X and 1.3 PFLOPS FP8 into a 350W PCIe Card”, 12 October 2026. https://www.storagereview.com/news/intel-gpu-d-series-480gb-lpddr5x-1-3-pflops-fp8-350w-pcie-card
- ServeTheHome (Ryan Smith), “Intel’s Crescent Island AI Server GPU Gets a Name and Specs: Meet the Intel GPU D-Series”, 12 October 2026. https://www.servethehome.com/intels-crescent-island-ai-server-gpu-gets-a-name-and-specs-meet-the-intel-gpu-d-series/
