AI Server
8x NVIDIA® RTX PRO Blackwell
The Godì 1.8SP5-D is a high-performance GPU server designed for AI and inference workloads in modern data centers. Powered by dual AMD EPYC™ processors, it can host up to 8 double-width GPUs, supporting the full NVIDIA® Blackwell GPU family, from the RTX PRO 5000 (300W, up to 72 GB GDDR7) and the RTX PRO 6000 Max-Q, Dual-slot form factor for maximum density, delivering exceptional acceleration for AI training, inference, and HPC workloads.
Its architecture provides very high GPU density, making it ideal for companies deploying large-scale AI models and real-time inference workloads. The system also features front-accessible hot-swap drive bays, allowing easy maintenance and continuous operation.
For high-speed connectivity and efficient data transfer, the server integrates up to two network interface cards at the rear, ensuring seamless networking capabilities for GPU-accelerated infrastructures.
Image courtesy of NVIDIA. 
NVIDIA® RTX PRO 5000
Edition
The RTX PRO 5000 Blackwell brings the full power of the Blackwell architecture to workstation and mid-range server deployments.
Available with 48 GB or 72 GB of GDDR7 ECC memory (1,344 GB/s), 14,080 CUDA cores, 5th Gen Tensor Cores, and 2,064 AI TOPS, it handles demanding AI, rendering, and visualization tasks at 300W, an ideal balance between performance and power envelope.
NVIDIA® RTX PRO 6000 Blackwell Max-Q
Designed for thermally constrained environments, the RTX PRO 6000 Max-Q packs the same 96 GB GDDR7 memory and full Blackwell feature set as its full-power sibling into a dual-slot compact form factor at 300W.
It uses active cooling, making it the go-to option for workstation deployments or servers where power and space are at a premium without sacrificing GPU memory capacity.
Image courtesy of NVIDIA. 
NVIDIA Omniverse™
Accelerate AI, rendering, and visualization in your professional software with RTX Enterprise drivers, ISV certifications, and an optimized ecosystem. The result: broad compatibility, consistent performance, 24/7 stability, and simplified deployment (IT, monitoring, vGPU).
In the cloud or data center, leverage NVIDIA vGPU virtualization and GPU splitting (partitioning/MIG depending on the platform) to share a single card across multiple users or workloads while maintaining a secure experience.
AMD EPYC™ 5th generation
Discover the AMD EPYC™ 9005 Series Processors, designed for unmatched performance, scalability, and energy efficiency in the most demanding data center workloads.
With up to 160 cores and 320 threads, these processors excel in enterprise applications, HPC, and AI tasks.
The advanced architecture and enhanced memory and I/O bandwidth deliver superior performance per watt.
Up to 192 Cores
The world’s highest performance server processors for computing.
Up to 128 PCIe 5.0 Lanes
128 PCIe 5.0 lanes in single-socket platforms.
Up to 400W TDP
The best ratio between number of cores and power consumption.
Up to 5 GHz in Boost mode
Enjoy even more amazing performance!