Dell PowerEdge R760xa AI Server – Dual Intel Xeon, 8TB DDR5, Up to 4 Double-Width GPUs

The Dell PowerEdge R760xa AI Server is a powerful 2U rack-mounted enterprise GPU server designed for organizations running artificial intelligence, machine learning, deep learning, high-performance computing, and other GPU-intensive workloads.

The server supports dual Intel Xeon Scalable processors, providing substantial CPU processing capabilities for AI data preparation, enterprise applications, analytics, virtualization, and other demanding workloads.

With support for up to 8TB DDR5 RAM, the R760xa provides significant memory capacity for large datasets, AI frameworks, virtualization environments, and memory-intensive applications.

A key feature of the platform is its support for up to 4 double-width GPUs, allowing organizations to deploy high-performance accelerator hardware for AI training, machine learning, inference, scientific computing, and other accelerated workloads.

The 2U form factor provides a balance between computing density and expansion capability, making the R760xa suitable for enterprise data centers and AI infrastructure deployments.

Key Specifications

• Product: Dell PowerEdge R760xa AI Server
• Form Factor: 2U Rack Server
• Processor: Dual Intel Xeon Scalable Processors
• Memory: Up to 8TB DDR5 RAM
• GPU Support: Up to 4 Double-Width GPUs
• Server Type: Enterprise GPU / AI Server
• Primary Applications: AI Training, Machine Learning and Deep Learning
• Workloads: AI Training, AI Inference, Data Analytics and Accelerated Computing
• Deployment: Enterprise Data Centers and AI Infrastructure

Key Benefits

• High-performance 2U GPU server
• Dual Intel Xeon Scalable processor architecture
• Up to 8TB DDR5 memory
• Supports up to 4 double-width GPUs
• Designed for AI and machine learning workloads
• Suitable for deep learning and AI inference
• Ideal for GPU-accelerated computing
• Suitable for enterprise data center environments
• Scalable platform for growing AI infrastructure
• Designed for demanding compute-intensive workloads