RTX PRO 6000 Blackwell

The RTX PRO 6000 Blackwell is the flagship of NVIDIA's RTX PRO Blackwell professional generation, the workstation counterpart to the GeForce RTX 50 series. Launched in March 2025, it sits at the top of NVIDIA's professional and workstation lineup, bringing the full extent of the Blackwell architecture to professional visualization, simulation, and AI development.

It is equipped with 96GB of GDDR7 memory with ECC support across a 512-bit bus, delivering 1792 GB/s of bandwidth. The card carries 24,064 CUDA cores and reaches 125 TFLOPS of FP32 compute, with Blackwell's 4th-generation RT cores and 5th-generation Tensor cores, plus AV1 hardware encoding. It is a dual-slot board on a PCIe 5.0 x16 interface with a 600W TDP, and runs NVIDIA's ISV-certified professional and Enterprise drivers.

The RTX PRO 6000 Blackwell is built for the most demanding professional workloads, including professional visualization, CAD/CAE, 3D rendering, real-time ray tracing, simulation, AI/ML development and inference, data science, and video production. Its very large 96GB frame buffer suits enormous scenes and datasets as well as sizeable local AI models, targeting users who need maximum professional throughput in a single workstation card.