Intel Accelerates Open Infrastructure for the Agentic AI Era
Intel unveiled new details on its GPU D-series (formerly Crescent Island), a data center inference GPU with up to 480 GB LPDDR5X memory, 1.5 TB/s bandwidth, and 1.3 petaflops of FP8 compute in a 350-watt envelope, with customer sampling underway. The company also showcased new Xeon-based rack designs at the OCP Global Summit, with select Xeon 6+ configurations scaling beyond 46,000 cores per rack at 133.45 kW.
Key figures
- Gpu memory
- up to 480 GB LPDDR5X (Intel-branded PCIe card has 160GB; ODM options up to 480GB)
- Fp8 compute
- 1.3 petaflops
- Power envelope
- 350 watts
- Memory bandwidth
- 1.5 TB/s
- Xeon rack core density
- 46,000+ cores per rack at 133.45 kW
- Max model params single card
- 300 billion parameters
- Ocp contributions since 2011
- 116
AI analysis
The rest of the AI analysis, red flags and sentiment are part of Signal8 Pro.
AI-generated analysis of a public disclosure. Not investment advice; verify against the original document.