NVIDIA Unveils 2U RTX Pro 6000 Blackwell Servers, Accelerating Enterprise AI Adoption

NVIDIA's Strategic Move in Enterprise AI

NVIDIA has announced a significant advancement in enterprise AI computing with the introduction of its RTX Pro 6000 Blackwell Server Edition GPU in 2U rack mount servers 1

1

. This move marks a crucial step in transitioning enterprise data centers from traditional CPU-based systems to more powerful and efficient GPU-accelerated platforms.

Compact Power: 2U Servers with Blackwell GPUs

The new 2U servers, which will be offered by major system providers including Cisco, Dell Technologies, HPE, Lenovo, and Supermicro, are designed to house two RTX Pro 6000 Blackwell GPUs 2

2

. This compact form factor is particularly appealing for enterprises with space, power, and cooling constraints, allowing them to build high-performance AI factories without extensive infrastructure overhauls.

Performance and Efficiency Gains

NVIDIA claims that these new RTX Pro servers deliver up to 45 times better performance and 18 times higher energy efficiency compared to CPU-only 2U systems 3

3

. This substantial improvement is attributed to the shift from CPU-only AI processing to GPU-accelerated computing, potentially leading to significant consolidation of server fleets into denser, higher-performance systems.

Technical Specifications and Advantages

The RTX 6000 Pro Server Edition GPU, essentially a fully enabled version of NVIDIA's desktop RTX 5090, boasts impressive specifications:

• 24,064 CUDA cores
• 600W TBP (Total Board Power)
• 512-bit memory interface
• 96GB of 28Gbps GDDR7 memory 1

  1

Importantly, these GPUs are air-cooled, making them a more cost-effective alternative to NVIDIA's liquid-cooled B200 and B300 Blackwell GPUs for many enterprise applications 1

1

.

Broad Application Spectrum

The new RTX Pro Servers are designed to accelerate a wide range of enterprise workloads, including:

• Agentic AI
• Content creation
• Data analytics
• Graphics rendering
• Scientific simulation
• Industrial and physical AI 2

  2

AI-Optimized Infrastructure

These servers form the backbone of NVIDIA's AI Data Platform, a customizable reference design for building modern storage systems for enterprise AI 4

4

. At SIGGRAPH, Dell announced updates to its AI Data Platform, integrated with NVIDIA's reference design, showcasing the PowerEdge R7725 2U server featuring two RTX Pro 6000 GPUs 2

2

.

Ecosystem and Availability

NVIDIA's Blackwell platform leverages a robust ecosystem, including CUDA-X libraries, over 6 million developers, and nearly 6,000 applications 4

4

. While configurations with eight RTX Pro 6000 GPUs in 4U form factors are available now, the new 2U mainstream RTX Pro Servers are expected to be available later this year 4

4

.

This strategic move by NVIDIA not only enhances the company's position in the enterprise AI market but also provides businesses with powerful tools to accelerate their AI initiatives, potentially reshaping the landscape of enterprise computing.