Following NVIDIA’s Computex keynote, Dell showcased its latest AI solutions featuring NVIDIA’s latest AI architecture, designed to take the “AI factory” ecosystem to new levels.
Dell’s “AI Factory” Products Now Feature NVIDIA’s Blackwell Ultra & RTX PRO 6000 Solutions, Making It The Largest Portfolio Out There
Dell has expanded its AI infrastructure massively over the past few years, especially after NVIDIA introduced its Hopper generation solutions, which managed to gain massive adoption in the AI markets.
It seems like Dell isn’t stopping just yet, as the firm has announced new and advanced PowerEdge AI racks, which feature NVIDIA’s latest Blackwell GPUs, the HGX B300, which can support up to a 192-GPU configuration, making them one of the fastest options out there. Dell has also become one of the first firms to offer NVIDIA’s RTX PRO 6000 “Blackwell” GPUs as well.
Starting with Blackwell Ultra, Dell has unveiled the PowerEdge XE9780 and XE9785 “air-cooled” servers, which are said to come with up to 192 Blackwell Ultra HGX B300 GPUs. Interestingly, there are also liquid-cooled models, the PowerEdge XE9780L and XE9785L, which are said to support up to 256 Blackwell Ultra GPUs per rack.
- Air-cooled Dell PowerEdge XE9780 and XE9785 servers simplify integration into existing enterprise data centers, while liquid-cooled Dell PowerEdge XE9780L and XE9785L servers accelerate rack-scale deployment. The new PowerEdge servers support up to 192 NVIDIA
Blackwell Ultra GPUs with direct to chip liquid cooling and can be customized with up to 256
NVIDIA Blackwell Ultra GPUs per Dell IR7000 rack. As the successors to Dell’s fastest ramping solution ever,3 the Dell PowerEdge XE9680, these platforms can deliver up to four times faster large language model (LLM) training with the 8-way NVIDIA HGX B300.4- The Dell PowerEdge XE9712 featuring NVIDIA GB300 NVL72 offers efficiency at rack scale for training and 50 times more AI reasoning inference output and 5x improvement in throughput. With new Dell PowerCool technology, this platform helps businesses achieve greater power efficiency.
- The Dell PowerEdge XE7745 server will be available with NVIDIA RTX Pro™ 6000 Blackwell
Server Edition GPUs in July 2025. This platform – supported in the NVIDIA Enterprise AI Factory validated design – provides a universal platform to help meet the needs of physical and agentic AI use cases like robotics, digital twins and multi-modal AI applications with support for up to 8 GPUs in a 4U chassis.- Dell plans to support the NVIDIA Vera CPU, offering speed, efficiency and performance.
- Dell plans to support the NVIDIA Vera Rubin platform with a new Dell PowerEdge XE server
designed for Dell Integrated Rack Scalable Systems.
Through this, the firm has managed to bring in a whopping 4x faster LLM training performance compared to the previous generation offerings, which shows that the generational increment in performance has been massive over the past few years, which is why Dell is a leading integrator.
Interestingly, Dell has also announced plans to release an AI solution based on NVIDIA’s latest RTX PRO Blackwell GPUs, making them the first of their kind. The PowerEdge XE7745 is expected to be released by July 2025, and it is set to target the industrial segment of the market, particularly applications like multi-modal AI. The firm has also announced plans to develop PowerEdge designs featuring NVIDIA’s Vera CPUs and Rubin GPUs as well, so the firm has extensive plans for the future as well.
We’re on a mission to bring AI to millions of customers worldwide. Our job is to make AI more accessible. Our job is to make AI more accessible. With the Dell AI
Factory with NVIDIA, enterprises can manage the entire AI lifecycle across use cases, from deployment training, at any scale.– Dell’s CEO Michael Dell
Dell is probably one of the first to offer the most extensive NVIDIA-focused AI portfolio, and the firm has managed to take its “AI factory” ambitions to a new level with the recent Blackwell Ultra-based products.
