Significant price hikes on 5090, L40S and Enerperise Blackwell Series GPUs continues into Q1 2026. Please note Credit Card payments will only work if USD or AED currency is selected on top right corner of the website. For US customers; before placing an order for any crypto miners, inquire with a live chat sales rep or toll-free phone agent about any potential tariffs. HGX B200 lead times are now between 8-20 weeks for Golden Sku selections, with custom BOMs exceed 26 weeks. HGX H200 offerings in stock, as well as limited HGX B300. We are now certified partners of Supermicro in both NA and MENA regions.
0%
Key Applications
The Supermicro GPU A-Server AS-8126GS-NB3RT with NVIDIA HGX B300 NVL8 is a top-tier 8U rackmount server engineered for AI, deep learning, and HPC workloads. Housing eight Blackwell B300 Ultra SXM GPUs interconnected via NVLink and NVSwitch for blistering throughput, this Supermicro GPU A-Server supports dual AMD EPYC 9005/9004 series processors. The system accommodates up to 6 TB of DDR5 memory across 24 DIMM slots, and offers eight hot-swappable E1.S NVMe drive bays plus dual M.2 slots for flexible storage. With eight 800 Gb/s OSFP network interfaces and redundant 6.6 kW Titanium-level power supplies, this NVL8 GPU server is built for mission-critical AI model training and large-scale inference deployments.
Key Features
Dual AMD EPYC™ 9005/9004 Series Processors
8x Blackwell 300 Ultra SXM GPUs
Supports up to 24 DIMM slots, 6400 MT/s 6TB DDR5 memory (1DPC only)
(Please check System Memory Section for detail)
8x OSFP 800GbE
2x PCIe 5.0 x16 FHHL slots
8x front hot-swap E1.S NVMe drive bays
6x 6600W Redundant (3 + 3) Titanium Level (96%) power supplies
(Power supply full redundancy based on configuration and application load)

No reviews available.