NVIDIA RTX PRO 6000 Blackwell Server Edition
Universal AI and Visual Computing for Data Centres
The NVIDIA RTX PRO 6000 Blackwell Server Edition, which is based on the revolutionary NVIDIA Blackwell architecture, accelerates enterprise data centre workloads by combining advanced AI and visual computing capabilities. The NVIDIA RTX PRO 6000 Blackwell, which comes with 96GB of incredibly fast GDDR7 memory, offers unmatched performance and versatility to speed up a wide range of use cases, including rendering, 3D graphics, video, agentic AI, physical AI, and scientific computing.
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
Performance of Scalable Workstations
Take advantage of the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition to experience the next level of AI and creative performance. With 96GB of lightning-fast GDDR7 memory and a density-optimized design, it offers unmatched AI and neural rendering capabilities to speed up your most demanding processes. Expand your computing capacity and open up new possibilities in AI, data science, and graphics by seamlessly scaling from one to four GPUs.
NVIDIA RTX PRO 6000 Blackwell Workstation Edition
The Best Graphics and AI Performance
The most potent desktop GPU ever made, the NVIDIA RTX PRO 6000 Blackwell Workstation Edition redefines performance and capability for experts. Master the most complicated models and creative tasks with unmatched AI processing. The RTX PRO 6000’s breakthrough NVIDIA Blackwell architecture and 96GB of rapid GDDR7 memory enable the impossible with unrivalled performance, precision, and efficiency.
NVIDIA RTX PRO 6000 Blackwell Series Features
5th Gen Tensor Cores
In addition to supporting FP4 accuracy and DLSS 4 Multi Frame Generation technology, fifth-generation Tensor Cores can achieve up to three times the performance of their predecessors. Promote improved content development and graphics, prototype new AI models, and speed up local LLMs.
4th Gen RT Cores
With up to two times the performance of the previous generation, fourth-generation RT Cores speed up rendering for manufacturing prototyping, AECO design, and M&E content development. Neural graphics-based technologies, such RTX Mega Geometry, which allows for up to 100X more ray-traced triangles, can be used to create immersive 3D designs and photoreal, physically correct scenes.
Cores for CUDA
Using the newest SM and CUDA core technology, the NVIDIA Blackwell is the most potent professional RTX GPU ever developed. Increased processing throughput and new neural shaders that incorporate neural networks into programmable shaders are two features of the SM that will propel advancements in AI-augmented graphics during the next ten years.
GPU Memory of 96GB
Improved GDDR7 memory greatly increases capacity and bandwidth, enabling your apps to operate more quickly and handle bigger, more complicated datasets. Take on enormous 3D and AI projects, investigate expansive VR landscapes, and manage more complex multi-app workflows with 96GB of GPU memory.
9th-Gen NVENC
For professional video applications, ninth-generation NVIDIA NVENC engines greatly increase video encoding speed and quality. They enhance the quality of HEVC and AV1 encoding and provide new support for 4:2:2 H.264 and HEVC encoding.
6th-Gen NVDEC
Sixth-generation NVIDIA NVDEC engines support 4:2:2 H.264 and HEVC decoding and can double the throughput of H.264 decoding. Professionals may employ cutting-edge AI-powered video editing tools, speed up the ingestion of video data, and enjoy high-quality video viewing.
GPU with Multiple Instances
The RTX PRO 6000 Max-Q’s performance and value are increased by Multi-Instance GPU (MIG), which allows for the development of up to four (4) completely isolated instances. Every MIG instance offers accelerated computational resources to all users to its own high-bandwidth memory, cache, and compute cores as well as guaranteed quality of service (QoS).
Gen 5 PCIe
Support for PCI Express Gen 5 doubles the bandwidth of PCIe Gen 4, enhancing CPU memory data transfer rates and enabling quicker performance for data-intensive tasks like 3D modelling, data science, and artificial intelligence.
DisplayPort 2.1
8K at 240Hz and 16K at 60Hz displays are supported by DisplayPort 2.1 for professional quality, clarity, and performance. While more bandwidth enables seamless multi-monitor setups for multitasking and collaboration, HDR and better colour depth provide correct colour for video editing, 3D modelling, and live broadcasting.
NVIDIA RTX PRO 6000 Blackwell Series Specifications
| NVIDIA RTX PRO 6000 Blackwell Server Edition | NVIDIA RTX PRO 6000 Blackwell Workstation Edition | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | |
|---|---|---|---|
| GPU Architecture | NVIDIA Blackwell | NVIDIA Blackwell | NVIDIA Blackwell |
| GPU Memory | 96 GB GDDR7 with error-correcting code (ECC) | 96 GB GDDR7 with error-correcting code (ECC) | 96 GB GDDR7 with error-correcting code (ECC) |
| Display Ports | 4x DisplayPort 2.1 | 4x DisplayPort 2.1 | 4x DisplayPort 2.1 |
| Power Consumption | 400-600 W | 600 W | 300 W |
| Graphics Bus | PCIe Gen 5 x16 | PCIe Gen 5 x16 | PCIe Gen 5 x16 |
| Form Factor | 4.4” (H) x 10.5” (L) dual slot | 5.4” (H) x 12” (L) dual slot | 4.4” (H) x 10.5” (L) dual slot |
| Thermal | Passive | Double flow-through | Active |
| AI TOPS | 4000 | 3511 | |
| Ray Tracing Cores | 4th Gen | 4th Gen | |
| NVIDIA Encoder(NVENC) | 4x | 4x 9th Gen | 4x 9th Gen |
| NVIDIA Decoder(NVDEC) | 4x | 4x 6th Gen | 4x 6th Gen |
| Memory Bandwidth | Up to 1.6TB/s | 1792 GB/sec | 1792 GB/sec |
