Custom configured, quickly delivered!
Your shopping cart is empty
Buy Online or Call 800-237-0402
Search
Featuring up to 8x NVIDIA HGX B200 Blackwell SXM form factor GPUs, the 4U Supermicro GPU A+ Server 4126GS-NBR-LCC supports dual AMD EPYC 9004 or 9005 series processors. Each CPU delivers up to 192 cores, 384 threads, and a 500W TDP. The server requires a complete liquid-cooled rack integration with a 250kW coolant distribution unit (CDU). Up to 8x systems can be installed in the SRS-48UDLC-4U8N-L1, a 64-GPU scalable unit.
Designed for industrial automation, healthcare applications, conversational AI, and more, the Supermicro 4126GS-NBR-LCC offers 8x hot-swappable 2.5” NVMe drive bays, plus 2x M.2 NVMe slots on the front panel. The maximum memory supported is up to 9TB when all 24x DIMMs are populated with RDIMM memory. With 12-channel memory architecture and 12x DIMM slots per socket memory can run at speeds of up to 6000MT/s. On the rear of the chassis, administrators can access 8x PCIe 5.0 x16 LP slots and 2x PCIe 5.0 x16 FHHL slots. 8x single-port NVIDIA ConnectX-7 NICs or NVIDIA BlueField-3 SuperNICs, 2x dual-port NVIDIA BlueField-3 DPUs, are compatible on this machine. The GPUs feature a PCIe 5.0 interface with NVIDIA NVLink with NVSwitch GPU to GPU interconnect.
To power this system, there are 4x 6600W redundant (2+2) Titanium Level PSUs located at the rear of the chassis. Administrators can manage the 4126GS-NBR-LCC by way of many managements software including Super Diagnostics Offline (SDO), Supermicro ThinAgent Service (TAS), and SuperServer Automation Assistant (SAA). SAA provides the ability to configure and update a single node or an entire datacenter both remotely or locally.
If you know what you want but can't find the exact configuration you're looking for, have one of our knowledgeable sales staff contact you. Give us a list of the components you would like to incorporate into the system, and the quantities, if more than one. We will get back to you immediately with an official quote.