Key Features
- 8 x NVIDIA HGX™ Rubin GPU, TDP up to 2300W
- Dual Intel® Xeon® 6 processors
- 32 x DDR5 DIMM slots, up to 6400 MT/s
- GPU memory 2.3 TB HBM4 (8 x 288 GB)
- 8 x Integrated NVIDIA ConnectX®-9 SuperNIC™ Ports (800Gb/s)
- 1 × NVIDIA BlueField®‑4 Adapters (NDR, 2 × 400G) for N‑S Networking
- 8 x E1.S NVMe, 2 x M.2 2280/22110 NVMe
The NVIDIA HGX™ Rubin NVL8 combines 8 NVIDIA Rubin GPUs with sixth-generation high-speed NVLink interconnects, ushering data centers into a new era of accelerated computing and generative AI.
2CRSi delivers rack-scale architecture with maximum deployment flexibility and extensive configuration options, supporting high-end x86 processors such as next-generation Intel® Xeon®.
NVIDIA HGX Rubin NVL8
DLC Server
Cooled by Direct Liquid Cooling
DLC is high-performance cooling technology designed for AI and HPC servers.
By circulating liquid through cold plates in direct contact with CPUs and GPUs, it enables efficient heat removal at the source.
Suitable for high-density environments exceeding 100 kW per rack, DLC ensures stable performance, reduces energy consumption, and improves overall data center efficiency while remaining compatible with standard rack architectures.
Intel® Xeon® 6 Processor Family
The Intel Xeon 6 family combines two complementary architectures to meet modern data center needs.
P-core models (Granite Rapids) deliver maximum performance for AI, HPC, and enterprise workloads, while E-core models (Sierra Forest) provide unmatched efficiency and density for cloud-native and scale-out applications.
With support for DDR5, PCIe 5.0, CXL 2.0, and built-in AI acceleration (Intel AMX), Xeon 6 processors offer the scalability, performance, and efficiency required for next-generation computing.