- Nvidia CPUs designed for scalable solutions with PCIe connectivity
- Delivers 144 cores and four GPUs for AI acceleration
- 1.3 TB memory makes NVL4 ideal for data-heavy applications
Nvidia has unveiled the GB200 NVL4, an advanced platform designed to meet the needs of modern data centers and computational workloads.
The company’s decision to introduce the GB200 NVL4 comes after Nvidia recently restructured its product lineup, setting aside other NVL platforms to favor newer options like the NVL4.
The GB200 NVL4 combines two Arm-based Grace CPUs with four Blackwell GPUs. It is part of Nvidia’s Grace Blackwell lineup, which aims to provide flexible and scalable solutions for diverse deployment scenarios.
High-speed and scalable
The GB200 NVL4 is designed as a mid-range option in the Grace Blackwell family, sitting below high-performance configurations like the NVL72 and NVL36. Each unit features two Grace CPUs, each equipped with 72 Arm Neoverse V2 cores, for a total of 144 cores. The addition of four Blackwell GPUs ensures robust acceleration for AI, HPC, and other compute-intensive tasks.
The six MCIO connectors beneath each CPU provide PCIe connectivity, allowing for high-speed data transfer. It also supports the inclusion of NICs, SSDs, and other essential components while maintaining efficiency.
Power consumption is a critical factor in modern data centers, but Nvidia estimates the GB200 NVL4 will consume just over 6 kW per server when fully configured. While this represents a substantial power draw, it is a marked improvement over larger platforms, with earlier systems like the Nvidia DGX-1 or HGX-1 consuming around 3.5 kW.
Furthermore, this device also supports up to 1.3 TB of combined memory, ensuring efficient data handling and processing while making it a strong candidate for memory-intensive applications. The NVL4 is expected to fill a niche for organizations seeking powerful yet relatively lower-power solutions compared to the higher GPU count NVL platforms.
The GB200 NVL4 and the higher-end NVL72 may appear similar at first glance, however, there are notable differences. The NVL72 features edge connectors for its spine configuration and focuses on larger-scale deployments with double the compute resources. In contrast, the NVL4 is designed as a more compact and power-conscious node while still delivering significant performance for its size.