NVIDIA RTX PRO 6000 Blackwell Server

The NVIDIA RTX PRO 6000 Blackwell Server is a workstation graphics card that launched in Q1 2025. It is built on the Blackwell 2.0 GPU microarchitecture (codename GB202) and is manufactured on a 5 nm process.

Memory

The RTX PRO 6000 Blackwell Server has 96 GB of GDDR7 memory, with a 1,750 MHz memory clock and a 512 bit interface. This gives it a memory bandwidth of 1.79 Tb/s, which affects how fast it can transfer data to and from memory. GPU memory stores temporary data that helps the GPU with complex math and graphics operations. More memory is generally better, as not having enough can cause performance bottlenecks.

Cores and Clock Speeds

The RTX PRO 6000 Blackwell Server includes 24,064 CUDA cores, the processing units for handling parallel computing tasks. The GPU operates at a core clock speed of 1,590 MHz and can dynamically boost its clock speed up to 2,617 MHz. Complementing the processing units are 752 texture mapping units (TMUs) for efficient texture filtering and 192 render output units (ROPs) for pixel processing. Additionally, the GPU features 752 tensor cores optimized for AI-accelerated workloads and 188 RT cores dedicated to real-time ray tracing calculations.

Compatibility & Power Consumption

The RTX PRO 6000 Blackwell Server occupies 2 PCIe expansion slots. It supports DisplayPort 2.1b display connections. NVIDIA recommends a power supply of at least 1,000 W to handle the GPU's thermal design power (TDP) of 600 W.