NVIDIA HGX B300 platform powers the world’s AI factories
The Godì 1.8E2D-NV8 is a high-density 8U dual-socket server designed to push the limits of the most demanding workloads.
Powered by two Intel® Xeon® 6 Scalable processors and up to 8 NVIDIA Blackwell Ultra B300 GPUs, it delivers massive computing power for:
- Large-scale LLM training and AI inference,
- High-performance computing and complex simulations,
- Large-scale data analytics,
- As well as critical enterprise and research applications.
Engineered to combine performance, scalability, and energy efficiency, the Godì 1.8E2D-NV8 stands out as the reference platform for hyperscale data centers and advanced computing environments.
Image courtesy of NVIDIA. 
NVIDIA HGX B300 NVL8 Platform
With models now exceeding a trillion parameters, the HGX B300 platform, equipped with 8 NVIDIA Blackwell Ultra GPUs, integrates the second generation Transformer Engine, NVFP4 format support, the fifth generation NVLink™, and up to 288 GB of HBM3e memory per GPU.
This combination ensures performance and scalability across any data center, enabling and making accessible next-generation LLMs, multimodal AI, and large-scale inference.
Intel® Xeon® 6 Processor Family
The Intel Xeon 6 family combines two complementary architectures to meet modern data center needs.
P-core models (Granite Rapids) deliver maximum performance for AI, HPC, and enterprise workloads, while E-core models (Sierra Forest) provide unmatched efficiency and density for cloud-native and scale-out applications.
With support for DDR5, PCIe 5.0, CXL 2.0, and built-in AI acceleration (Intel AMX), Xeon 6 processors offer the scalability, performance, and efficiency required for next-generation computing.
Up to 144 Cores
Designed to handle for intense data center workloads.
Up to 96 PCIe 5.0 Lanes
Greater flexibility and faster operation.
Up to 500W TDP
Optimal power consumption.
Up to 5.7GHz in Boost mode
Performance at its peak.
8x 800 Gb/s via onboard NVIDIA ConnectX®-8 SuperNIC™
Experience up to 800 Gb/s of fabric bandwidth and ultra-low-latency connectivity, accelerating model training, scaling inference, and keeping clusters in perfect sync. The ConnectX-8 SuperNIC supports NVIDIA Quantum-X800 InfiniBand and Spectrum-X™ Ethernet natively, and features a built-in PCIe Gen6 switch, eliminating bottlenecks and simplifying your architecture.
Get the most of your HGX B300 by enabling ConnectX-8 features!
Image courtesy of NVIDIA. 
NVLink 5ᵗʰ Generation: Redefining Multi-GPU Performance
NVIDIA’s 5ᵗʰ gen NVLink sets a new standard for GPU connectivity, delivering up to 1.8 TB/s bidirectional bandwidth per GPU, 14× faster than PCIe Gen-5.
With 18 NVLink connections per GPU, data moves effortlessly, powering the most demanding AI training and HPC workloads.
At rack scale, the NVLink Switch unlocks 14.4 TB/s switching capacity, enabling up to 576 GPUs to function as a single, massive accelerator.
This architecture doubles throughput over the previous generation. It ensures ultra-low latency, full memory coherence, and unmatched scalability, perfect for trillion-parameter AI, advanced scientific simulations, and next-generation data centers.