Build Your IT Infrastructure
Elevate your IDC with our state-of-the-art server solutions - for unmatched performance.
Hot Sales Deals
High-Performance AI Servers
ASROCK H200GX L6
$236,000
USD
Form Factor: 6U rackmount chassis.
Integrated with NVIDIA HGX H200 8-GPU module.
Dual Socket E (LGA 4677), compatible with 5th and 4th Gen Intel® Xeon® Scalable Processors.
32 DIMM slots supporting DDR5 RDIMM and RDIMM-3DS.
8 HHHL PCIe 5.0 x16 and 5 FHHL PCIe 5.0 x16 slots for additional expansion.
8 hot-swappable 2.5" NVMe (PCIe 5.0 x4) drive bays and 4 hot-swappable 2.5" NVMe (PCIe 5.0 x4)/SATA drive bays.
2 RJ45 (1GbE) ports powered by Intel® i350-AM2.
ASUS HGX200 L11
$268,500
USD
Supports dual 4th or 5th Gen Intel® Xeon® Scalable Processors, each with up to 350W TDP
32 DIMM slots (16 per CPU), supporting DDR5 4400 RDIMM/3DS RDIMM modules
Equipped with eight NVIDIA HGX H100 Tensor Core GPUs interconnected via NVLink and NVSwitch, delivering 900GB/s bandwidth for efficient scaling
SKU2: 12 PCIe Gen5 slots
10 hot-swappable 2.5” drive bays
2 M.2 Gen5 x4 slots connected to CPU1
Two 10 Gigabit LAN ports powered by Intel X710-AT2 Controller
Redundant 3000W 80 PLUS Titanium power supplies, configurable as 4+2 or 3+3
Quanta H200 GPU L10
$267,500
USD
Processors: Dual 5th/4th Gen Intel® Xeon® Scalable processors, up to 350W TDP.
Memory: 32 DDR5 DIMM slots, supporting up to 8TB capacity.
GPUs: Eight NVIDIA® H100 or H200 Tensor Core GPUs with HGX baseboard.
Storage: 18 hot-plug 2.5" NVMe SSD drive bays.
Networking: Ten PCIe 5.0 x16 OCP 3.0 TSFF slots for GPUDirect RDMA.
Design: 7U rackmount form factor with toolless, hot-swap components for enhanced serviceability.
4000W Power Unit
This server is optimized for AI and HPC workloads, offering high performance and scalability.
Gigabyte H200 G593-SD1-AAX3
$264,000
USD
NVIDIA HGX™ H200 8-GPU
900GB/s GPU-to-GPU bandwidth with NVIDIA® NVLink™ and NVSwitch™
Dual 5th/4th Gen Intel® Xeon® Scalable Processors
Dual Intel® Xeon® CPU Max Series
8-Channel DDR5 RDIMM, 32 x DIMMs
Compatible with NVIDIA BlueField®-3 DPUs/SuperNICs
2 x 10Gb/s LAN ports via Intel® X710-AT2
8 x 2.5" Gen5 NVMe/SATA/SAS-4 hot-swap bays
4 x FHHL PCIe Gen5 x16 slots
8 x LP PCIe Gen5 x16 slots
4+2 3000W 80 PLUS Titanium redundant power supplies
Dell PowerEdge XE9680
$245,000
USD
Dual 5th Generation Intel® Xeon® Scalable processors with up to 64 cores per processor
Total Slots: 32 DDR5 DIMM slots.
Supports up to 4 TB of RDIMM memory.
Up to 5600 MT/s with 5th Generation Intel® Xeon® processors; up to 4800 MT/s with 4th Generation Intel® Xeon® processors.
8 NVIDIA HGX H100 80GB 700W SXM5 GPUs, interconnected via NVIDIA NVLink technology.
Up to 8 x 2.5-inch NVMe/SAS/SATA SSD drives, supporting a maximum capacity of 122.88 TB.1
Up to 10 x16 Gen5 full-height, half-length slots.
Embedded NIC: 2 x 1 GbE ports.
3200W Titanium 277 VAC or 260-400 VDC, hot-swappable and redundant.
Integrated Dell Remote Access Controller 9 (iDRAC9) with Lifecycle Controller.
Lenovo HGX H200 Baseboard
$209,000
USD
GPUs: 8 × NVIDIA H200 Tensor Core GPUs (141 GB HBM3e Memory per GPU)
Memory Bandwidth: Up to 4.8 TB/s
NVIDIA NVLink® (4th Gen), providing up to 900 GB/s GPU-to-GPU bandwidth
GPU-to-CPU Communication: NVIDIA NVSwitch™
~32 PFLOPS FP16, ~64 PFLOPS INT8, depending on the configuration
Baseboard typically used in 6U or 8U server chassis
Approx. 700W per GPU (5,600W total for all GPUs)
Primary Workloads: AI training, large language models (LLMs), deep learning, and advanced data analytics.
H100 Level 10
The NVIDIA H100 Level 10 Server is engineered for peak performance in AI and cryptocurrency mining operations. Powered by the NVIDIA H100 Tensor Core GPU, it delivers exceptional computational capabilities with up to 67 teraflops of double-precision performance and 80 GB of high-bandwidth HBM3 memory. The server supports Multi-Instance GPU (MIG) technology, allowing partitioning into isolated instances for efficient resource utilization. With PCIe Gen5 and NVLink connectivity, it ensures rapid data transfer, while its energy-efficient design balances high performance with optimized power consumption.
H200 Level 10
The NVIDIA H200 Level 10 Server is engineered to elevate AI and high-performance computing workloads. Featuring the NVIDIA H200 Tensor Core GPU with 141 GB of HBM3e memory and a bandwidth of 4.8 TB/s, it delivers exceptional performance for large language models and data-intensive tasks. The server offers up to 4 petaFLOPS of FP8 performance, supports Multi-Instance GPU (MIG) technology for efficient resource utilization, and maintains energy efficiency with a configurable TDP of up to 700W
