跳转到主要内容

Introducing the NVIDIA RTX PRO 6000 Blackwell Server Edition GPU with Supermicro

Designed to run wide range of enterprise applications

The NVIDIA RTX PRO™ 6000 Blackwell Server Edition is the ultimate universal data center GPU, delivering breakthrough multi-workload acceleration for the most demanding generative AI, physical AI, graphics, scientific computing, and video applications. Use up to eight NVIDIA RTX PRO 6000 GPUs in a server to deliver unmatched levels of compute power, memory capacity, and throughput to power mission-critical AI-enabled applications and accelerate use cases across industries—from healthcare, manufacturing, and geoscience to retail, media, and live broadcast.

Supermicro 4U GPU System optimized for NVIDIA RTX PRO™ 6000 Blackwell Server Edition

Supermicro and NVIDIA: Engineered Together for Optimal Enterprise Value

Unleash optimal performance for your enterprise with NVIDIA RTX PRO Servers co-engineered by Supermicro and NVIDIA. We pair the power of NVIDIA Enterprise Software with Supermicro's world-class engineering to accelerate your most demanding applications. Deploy a wide range of workloads with confidence, knowing our solutions leverage the latest technology to deliver exceptional performance for your business.

  • Supermicro is the first to market with NVIDIA RTX PRO 6000 Blackwell Server Edition based systems with over 20 of optimized systems
  • Form factors to suit a range of enterprise AI deployments and easily integrate into existing infrastructure
  • Combines the latest NVIDIA Enterprise software including: NVIDIA AI enterprise, NIMs, NeMo, Blueprints, and the new RTX PRO Software bundle
  • Support for NVIDIA ConnectX®-7 and NVIDIA BlueField®-3 adapters. Scale out with either NVIDIA Spectrum-X™ Ethernet or NVIDIA Quantum-2 InfiniBand

Expert Engineering

Designed for NVIDIA RTX PRO 6000 Blackwell Server Edition at maximum performance in challenging environments supporting up to 35°C ambient temperature

Supermicro’s high ambient temperature designs allow for the operation of enterprise AI systems in high temperature environments without restricting GPU performance, further reducing both data center operating costs and cooling infrastructure costs. These Supermicro systems have been optimized for maximum thermal efficiency and airflow to reduce the barriers to deploying latest-generation GPUs in existing enterprise data center environments.

CPU-GPU-NIC ratio: 2-8-5 (4U) or 1-4-3 (2U)
Up to 8x NVIDIA RTX PRO 6000 Blackwell Server Edition (600W TDP) GPUs
35°C Data Center Ambient Temperature
E3.L (4U) or E1.S (2U) NVMe
Intel® Xeon® CPUs

RTX PRO Server

4U and 2U rackmounts based on reference architectures, supporting up to 8 PCIe GPUs

NVIDIA RTX PRO Servers leverage the breakthrough performance and energy efficiency of the NVIDIA Blackwell architecture, enabling enterprises to build AI factories and accelerate a wide range of enterprise workloads—from agentic AI and LLM inference to industrial AI and digital twins. Available in multiple configurations, each system is enterprise-ready, and can easily replace existing enterprise data center servers with minimal modification to racks. Designed to deliver performance at scale, RTX PRO Servers are configured for seamless integration into full-stack AI solutions.

CPU-GPU-NIC ratio: 2-8-5, 2-2-3, or 1-2-3
Up to 8x NVIDIA RTX PRO 6000 Blackwell Server Edition (600W TDP) GPUs
RTX PRO Server Architecture
E1.S or U.2 NVMe
Dual or Single Intel® Xeon® CPUs

5U 8-GPU

Thermally-optimized architecture for AI inference, fine-tuning, HPC, and graphics processing

Supermicro GPU-optimized and RTX PRO Server systems are available in a range of form factors to support large-scale enterprise AI and visual computing workloads for enterprises of any size. Built on proven architectures and designed for maximum thermal performance in air-cooled environments, these systems support up to 8 NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs and can be configured as NVIDIA-Certified Systems™ for integration into full-stack solutions.

CPU-GPU-NIC ratio: 2-8-5 or 2-4-3
Up to 8x NVIDIA RTX PRO 6000 Blackwell Server Edition (600W TDP) GPUs
Dual-Root or Direct-Connect
Up to 24 NVMe Drives
Dual AMD EPYC™ or Intel® Xeon® CPUs

Deploy Production AI Faster with Supermicro NVIDIA-Certified Systems

Take the guesswork out of creating complete AI solutions with Supermicro NVIDIA-Certified Systems validated for performance, manageability, security, and scalability.

  • Guaranteed compatibility and support for NVIDIA AI Enterprise software to simplify the process of developing and deploying production AI.
  • Scale-out compute nodes with PCIe-optimized Reference Configurations
  • Supermicro NVIDIA-Certified and NVIDIA-Qualified systems available in 8-GPU, 4-GPU, and 2-GPU RTX PRO 6000 Blackwell Server Edition configurations
Featured Resources