# Intel's Crescent Island AI Server GPU Gets a Name and Specs: Meet the Intel GPU D-Series

DevFeed: [Intel's Crescent Island AI Server GPU Gets a Name and Specs: Meet the Intel GPU D-Series](<https://devfeed.tech/articles/intel-s-crescent-island-ai-server-gpu-gets-a-name-and-specs-meet-the-intel-gpu-d-series-85463.md>)

Original publisher: [Read original article](<https://www.servethehome.com/intels-crescent-island-ai-server-gpu-gets-a-name-and-specs-meet-the-intel-gpu-d-series/>)

Author: Ryan Smith

Published: 2026-10-12T19:25:28Z

Content type: news

Language: en

Sources: [ServeTheHome](<https://devfeed.tech/sources/servethehome.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [Deployment & Scaling](<https://devfeed.tech/topics/deployment-scaling.md>), [AWS Inferentia](<https://devfeed.tech/topics/aws-inferentia.md>), [NVLink](<https://devfeed.tech/topics/nvlink.md>)

Tags: [accelerators](<https://devfeed.tech/tags/accelerators.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [crescent-island](<https://devfeed.tech/tags/crescent-island.md>), [data-center-servers](<https://devfeed.tech/tags/data-center-servers.md>), [fp8](<https://devfeed.tech/tags/fp8.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpu-d-series](<https://devfeed.tech/tags/gpu-d-series.md>), [inference](<https://devfeed.tech/tags/inference.md>), [intel](<https://devfeed.tech/tags/intel.md>), [memory-bandwidth](<https://devfeed.tech/tags/memory-bandwidth.md>), [news](<https://devfeed.tech/tags/news.md>), [performance](<https://devfeed.tech/tags/performance.md>), [server](<https://devfeed.tech/tags/server.md>), [xe3](<https://devfeed.tech/tags/xe3.md>)

## AI overview

Intel has named its forthcoming Crescent Island data center inference accelerators the GPU D-Series, with the first card designated D270. The article reports 1.3 PFLOPs of FP8 matrix performance, 1.5 TB/s memory bandwidth, and a 350-watt design. Intel's own card will have 160 GB of LPDDR5X memory, while ODM partners can offer configurations up to 480 GB. Cards are sampling to customers, but Intel has not announced a launch date or price.

## Source excerpt

Intel today has unveiled its official performance specifications and branding for its upcoming "Crescent Island" data center AI inference cards. Going under the name Intel GPU D-Series, the D270 will offer 1.3 PLFOPs of dense FP8 and 1.5TB/second of memory bandwidth The post Intel's Crescent Island AI Server GPU Gets a Name and Specs: Meet the Intel GPU D-Series appeared first on ServeTheHome.