Supermicro SYS-221GE-TNHT-LCC GPU SuperServer DP Intel 2U liquid-cooled system with NVIDIA HGX™ H100 4-GPU or H200 4-GPU
The Supermicro SYS-221GE-TNHT-LCC is a high-performance 2U rackmount server featuring dual Intel® Xeon® Scalable processors, up to 8TB DDR5 memory, and support for 4 NVIDIA® HGX™ H100 or H200 GPUs. Designed for AI/Deep Learning, HPC, and data analytics, it offers direct-to-chip liquid cooling and PCIe Gen 5.0 x16 LP slots for optimal performance.

Supermicro SYS-221GE-TNHT-LCC GPU SuperServer Resources
Unleash GPU Compute Power
The Supermicro SYS-221GE-TNHT-LCC is a 2U rackmount server purpose-built for GPU-intensive workloads such as AI inference, HPC simulations, and large-scale virtual desktop infrastructure (VDI).


Optimized GPU Performance
Built to maximize AI inference, graphics rendering, and compute-intensive workloads with exceptional energy efficiency. Featuring NVIDIA GPUs interconnected via NVLink, and optimized PCIe Gen5 architecture. Supports up to 8 NVIDIA SXM GPUs (H100/H200). Dual 5th Gen Intel® Xeon® Scalable processors for balanced compute and memory performance. NVLink for GPU-to-GPU high-speed interconnect. Up to 32 DDR5 RDIMM slots for expansive memory capacity

Designed for Next-Gen Workloads
Ideal for enterprises requiring reliable, scalable GPU compute for AI applications, medical imaging, financial modeling, and virtual workstations.
- Enhanced reliability with redundant 2000W Titanium Level power supplies
- Flexible storage with multiple NVMe and M.2 drive options
- Efficient thermal design with direct-to-chip liquid cooling for GPUs
- Robust security with TPM 2.0 and Silicon Root of Trust
MFG Number | SYS-221GE-TNHT-LCC |
---|---|
Condition | Item Condition : Brand New |
Price | $0.00 |
Show Product Will Be Available Soon on FE | No |
Estimated time of Delivery | Estimated Delivery 4 Weeks. |
Product Card Description | The Supermicro SYS-221GE-TNHT-LCC is engineered for demanding AI and HPC workloads. It supports dual 5th/4th Gen Intel® Xeon® Scalable processors with up to 56 cores per CPU and up to 8TB of DDR5 memory. The system accommodates 4 NVIDIA® HGX™ H100 or H200 GPUs, interconnected via NVIDIA® NVLink®, ensuring high-bandwidth GPU communication. Its 2U rackmount form factor and direct-to-chip liquid cooling solution provide efficient thermal management, making it ideal for data centers requiring high-density compute solutions. |
Order Processing Guidelines | Order Processing Guidelines:
Inquiry First – Please reach out to our team to discuss your requirements before placing an order. |
Special Price | $0.00 |
Special Price From Date | May 2, 2024 |