NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
Outfitted with the successor to Ada Lovelace architecture, the NVIDIA RTX 6000 Blackwell Max-Q Workstation Edition offers 3x the performance of the previous generation with support for 5th generation tensor cores and support for FP4. FP4 enables faster AI model processing times for fine tuning LLMs and generative AI models, all while using less memory. It features 96GB of GDDR7 memory and supports MIG or multi-instance GPU enabling up to 4x GPU instances of 24 GB each.
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - System Overview
The NVIDIA RTX 6000 Blackwell Max-Q Workstation Edition has a PCIe 5.0 x16 interface and requires 300W of juice with a 16-pin power connector. PCIe 5.0 offers double the bandwidth compared to PCIe 4.0., delivering faster GPU to CPU communication. There are 4x DisplayPort 2.1b ports for attaching up to 4x 4K displays with a refresh rate of 120Hz or two monitors at 8K and a 60Hz refresh rate. DLSS 4 Multi Frame Generation allows for 3x the frame rates, and significantly improved video playback. With the powerful performance of the RTX 6000 Blackwell Max-Q Workstation, up to 4x GPUs can be enabled in a single system for complex simulations, AI training, and 3D rendering.
The RTX 6000 Max-Q delivers 24,064 NVIDIA Cuda Cores paired with memory bandwidth that is an incredible 1792GB/s enabling more complex graphics rendering and for running complex calculations and simulations. It offers 3511 TOPS or Trillions of Operations Per Second to deliver significant performance for AI applications. With MIG, users can perform multiple workloads on the same GPU, optimizing GPU utilization.
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - Specifications
GPU Engine
Architecture
NVIDIA Blackwell Architecture
NVIDIA CUDA Cores
24,064
Tensor Cores
5th Generation
Ray Tracing Cores
4th Generation
AI TOPS
3511 AI TOPS
Single-precision performance
110 TFLOPS
RT Core Performance
333 TFLOPS
Memory
Standard Memory Configuration
96 GB GDDR7 with ECC
Memory Interface
512-bit
Memory Bandwidth
1792 GB/s
MIG Instance Types
Up to 4x 24 GB
Up to 2x 48 GB
Up to 1x 96 GB
Technology Support
Graphic APIs
DirectX 12, Shader Model 6.6, OpenGL 4.6, Vulkan 1.3
Compute APIs
CUDA 12.8, OpenCL 3.0, DirectCompute
Display Support
Display Connectors
4x DisplayPort 2.1b
Graphics Bus
PCI Express 5.0 x16
Max Simultaneous Displays
4x 4096 x 2160 @ 120 Hz
4x 5120 x 2880 @ 60 Hz
2x 7680 x 4320 @ 60 Hz
Video Engines
4x NVENC (9th Gen)
4x NVDEC (6th Gen)
Card Dimensions
Length: 10.5"
Height: 4.4"
Slots: Dual-Slot, Full Height
Thermal & Power
Power Consumption
Total board power: 300 W
Thermal Solution
Active
Power Connector
1x PCIe CEM5 16-pin
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - Documentation
Get a quote for NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
If you know what you want but can't find the exact configuration you're looking for, have one of our knowledgeable sales staff contact you. Give us a list of the components you would like to incorporate into the system, and the quantities, if more than one. We will get back to you immediately with an official quote.
