Dell launches PowerEdge XE7740 server with Intel Gaudi 3 accelerators for enterprise AI

Dell Technologies has introduced the PowerEdge XE7740 server, featuring the newly launched Intel Gaudi 3 PCIe accelerators, becoming the first company to bring an integrated configuration of this kind to market. The 4U PowerEdge XE7740 is designed to deliver powerful AI acceleration, flexibility and efficiency while fitting seamlessly into existing enterprise data centre environments.

The XE7740 combines the ease of integration associated with the PowerEdge R-Series and the performance and scalability of the XE-Series. With advanced networking and powerful accelerator options, it aims to meet the growing demands of AI development across industries such as financial services, healthcare, manufacturing, telecommunications and retail.

Flexible performance for enterprise AI

The XE7740 can accommodate up to eight double-wide or PCIe accelerators, with configurations supporting up to eight individual Gaudi 3 accelerators or optional groups of four bridged accelerators using RoCE v2. This accelerator-to-accelerator bridging is critical for scaling larger AI models, offering flexibility and expanded memory capacity for demanding workflows.

To overcome power-per-rack limitations, the server offers flexible networking with up to a 1:1 accelerator-to-NIC ratio through eight full-height PCIe slots and an integrated OCP networking module. Designed to run efficiently in ~10kW racks, it integrates smoothly into existing air-cooled infrastructures without requiring costly upgrades.

Optimised for popular AI models such as Llama4, Llama3, Deepseek, Phi4, Qwen3 and Falcon3, the XE7740 ensures enterprises can accelerate AI adoption reliably and efficiently.

Use cases across industries

The PowerEdge XE7740 is tailored to support a wide range of AI workloads. These include large language model inferencing and fine-tuning, multimodal AI for image and speech recognition, data-intensive healthcare analysis such as genome sequencing, fraud detection and risk management in financial services, and real-time personalisation in retail and e-commerce.

With smooth integration into PyTorch and platforms like Hugging Face, enterprises can fine-tune models or run advanced inference with greater efficiency.

Accessible, scalable and cost-efficient

Dell emphasised that the XE7740 is not just about computing power but also about making AI more accessible to enterprises. Its price-to-performance ratio is designed to reduce barriers to adoption while offering scalability through modular configurations. Compatibility with existing enterprise data centre constraints helps organisations avoid retrofitting costs.

By enabling on-premises AI projects, the server also reduces cloud-related utilisation and egress expenses, supporting more predictable cost management while safeguarding data security.

Industry perspective

“With AI adoption accelerating across industries, enterprises need infrastructure that is both powerful and practical. The Dell PowerEdge XE7740 with Intel Gaudi 3 PCIe accelerators delivers the right balance of performance, scalability, and cost efficiency. It integrates seamlessly into existing environments, helping organisations overcome infrastructure barriers. This innovation makes enterprise AI more accessible, enabling businesses to scale confidently and unlock new possibilities,” said Venkat Sitaram, Senior Director & Country Head, Infrastructure Solutions Group Specialty Sales, India, Dell Technologies.

The XE7740 is positioned as a future-ready server that enables enterprises to handle today’s AI workloads while preparing for emerging use cases, ensuring lasting value in an increasingly competitive AI-driven business landscape.

ReadMore:

Taiwan Expo 2025: Taiwan Excellence Pavilion unveils smart innovations

How Judge India blending Cloud, AI and managed services for a digital future?

Reshaping AI-driven cybersecurity for enterprises and mid-markets

Freshworks and Sonata IT: partner-led SaaS growth and AI-first expansion in India, APAC