At CES on January 5, 2026, Nvidia unveiled the Vera Rubin rack-scale platform and announced the NVL72 AI supercomputer, slated for production in the second half of 2026. The system integrates 72 Rubin GPUs, 36 Vera CPUs, NVLink 6 and BlueField 4 DPUs, promising up to 50 PFLOPS NVFP4 per GPU and claiming an order-of-magnitude reduction in inference costs.
Key Points
- 1Introduces Vera Rubin platform and NVL72 with 72 Rubin GPUs per rack
- 2Promises up to 50 PFLOPS NVFP4 per GPU with HBM4, claiming tenfold reduction in inference costs
- 3Encourages rack-scale deployments and raises CUDA switching costs for hyperscalers and AI labs
Scoring Rationale
Major platform launch with concrete performance claims; strong industry impact but actual deployment timing and deliverability remain to be proven.
Sources
Public references used for this report.
Practice with real Logistics & Shipping data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
High-Value Overnight OrdersEasyDelivered International ShipmentsMediumOn-Time Delivery Rate by CarrierHard
250 free problems · No credit card
See all Logistics & Shipping problems
