search
GPU D-Series
Trends
- 1
Intel shares slid about 3% in a broader selloff of chip stocks, alongside declines at Nvidia and AMD, as rising yields and oil pressured markets. At the same time, several analysts and commentators argue Intel is undervalued, citing cheap CPU-related valuation, a case for buying before 2027, and new GPU hardware like a 350W D-Series card with 480GB LPDDR5X and 1.3 PFLOPS FP8 performance.
- 2
Intel's D-Series GPU is drawing attention for its unusually high specs: 480GB of LPDDR5X memory and 1.3 PFLOPS of FP8 performance delivered in a single 350W PCIe card. StorageReview highlighted the specifications, which position the card as an option for AI inference and data center workloads, and the news is circulating widely in Japan's tech community.
- 3Intel launches Crescent Island AI accelerator as GPU D-Series●Intel's Crescent Island AI accelerator officially powers new GPU D-Series products Intel's Crescent Island AI inference
Intel has confirmed that its Crescent Island AI inference accelerator will ship commercially as the GPU D-Series family. The chips are advertised with 1.3 PFLOPS of FP8 compute and up to 480 GB of LPDDR5X memory delivering around 1.5 TB/s of bandwidth, positioning them for memory-heavy AI inference workloads rather than training. The specs put Intel in direct competition with Nvidia's inference offerings, and tech watchers are weighing whether the memory-first design gives Intel a real opening in the inference market.
- 4Intel D-Series GPU bets on air cooling for AI inference●Explore how the new Intel D-Series GPU provides a high-memory, air-cooled solution for agentic AI inference, defying the
Intel has introduced the D-Series GPU, a high-memory, air-cooled chip aimed at agentic AI inference workloads in data centers. The design goes against the industry trend of moving to liquid cooling, and was showcased at OCP 2026, drawing attention from tech and security observers discussing whether air cooling can meet growing AI demands.