Giga Computing, a subsidiary of GIGABYTE and an industry leader in generative AI servers and advanced cooling technologies, announced new GIGABYTE G893 series servers using the NVIDIA HGX B200 platform. The launch of these flagship 8U air-cooled servers, the G893-SD1-AAX5 and G893-ZD1-AAX5, signifies a new architecture and platform change for GIGABYTE in the demanding world of high-performance computing and AI, setting new standards for speed, scalability, and versatility.

These servers join GIGABYTE's accelerated computing portfolio alongside the NVIDIA GB200 NVL72 platform, which is a rack-scale design that connects 36 NVIDIA Grace CPUs and 72 NVIDIA Blackwell GPUs. At CES 2025 (January 7-10), the GIGABYTE booth will display the NVIDIA GB200 NVL72, and attendees can engage in discussions about the benefits of GIGABYTE platforms with the NVIDIA Blackwell architecture.Revolutionary Features for Unprecedented Performance
The G893-SD1-AAX5 and G893-ZD1-AAX5 are equipped with state-of-the-art technologies designed to accelerate AI training, data analytics, and HPC simulations.

• NVIDIA HGX B200 8-GPU Support: Featuring eight NVIDIA Blackwell GPUs interconnected with NVIDIA NVLink, these servers deliver exceptional parallel processing power for x86 systems to help meet the demands of next-generation AI models and computational tasks.
• Blazing-Fast Interconnectivity: A groundbreaking 1800 GB/s GPU-to-GPU bandwidth delivers seamless communication and data sharing between GPUs, enabling faster processing times and enhanced efficiency.
• Dual CPU Options for Versatility: With support for both Intel Xeon processors and AMD EPYC CPUs, users can choose the optimal configuration to suit their workload requirements.
• Expanded Scalability: PCIe connectivitybuilt for NVIDIA BlueField -3 DPUs and ConnectX -7 for maximize data throughput and system scalability, helping future-proof investments for evolving technology demands.

Unlocking New Possibilities for AI and HPC Workloads
The G893-SD1-AAX5 and G893-ZD1-AAX5 are designed to meet the growing needs of industries ranging from healthcare and scientific research to financial modelling and autonomous systems. Whether it's training large-scale AI models, processing massive datasets, or running complex simulations, these servers deliver powerful performance to drive innovation forward.

Built for Efficiency and Reliability
In addition to their extraordinary computational power, these servers are engineered for exceptional energy efficiency and reliability. Advanced cooling solutions, high-performance components, and optimized designs help ensure that they can handle the most demanding workloads while maintaining operational stability and reducing total cost of ownership.

Going a Step Further - GIGAPOD
GIGAPOD is a rack-scale AI supercomputing solution specifically designed to meet the massive computational demands required for training generative AI models and large language models with billions of parameters. GIGAPOD integrates powerful GPUs, networking, and other scalable components. With the addition of the NVIDIA HGX B200 platform, GIGAPOD has refined its rack-scale design, offering customers enhanced performance, greater efficiency, and more options.