Description
The NVIDIA RTX PRO™ 6000 Blackwell Workstation Edition is the ultimate single-GPU powerhouse, delivering unmatched AI, rendering, and simulation performance for professionals who demand the very best. Built on the revolutionary NVIDIA Blackwell architecture, it sets a new benchmark for workstation-class compute by combining 24,064 CUDA® Cores, 5th Gen Tensor Cores, 4th Gen Ray Tracing Cores, and a massive 96 GB of GDDR7 memory with ECC.
With up to 4,000 AI TOPS and 1.8 TB/s of memory bandwidth, the RTX PRO 6000 enables lightning-fast fine-tuning of trillion-parameter LLMs, real-time cinematic rendering, and highly precise scientific simulations. Professionals in AI research, engineering, and creative industries can now iterate, visualize, and deploy with unparalleled speed and efficiency—all from a single desktop GPU.
The card’s 600W design is supported by an innovative double-flow-through cooling system, ensuring stable, uninterrupted performance during compute-intensive workloads. This makes it ideal for AI training, advanced simulations such as computational fluid dynamics, large-scale engineering design, and photorealistic content creation.
Features
- NVIDIA Blackwell Architecture with neural shader-enabled SMs
- 5th Gen Tensor Cores with FP4 precision and DLSS 4 Multi Frame Generation
- 4th Gen Ray Tracing Cores with RTX Mega Geometry for up to 100× more ray-traced triangles
- 96 GB of ECC GDDR7 memory with 1.8 TB/s bandwidth
- 24,064 CUDA Cores for extreme parallel compute performance
- Up to 4,000 AI TOPS for generative AI, LLMs, and inference
- 9th Gen NVENC & 6th Gen NVDEC with 4:2:2 support for advanced video pipelines
- Multi-Instance GPU (MIG) support: up to 4× 24 GB, 2× 48 GB, or 1× 96 GB partitions
- PCIe 5.0 x16 interface for maximum bandwidth
- Four DisplayPort 2.1b outputs supporting up to 16K @ 60 Hz or 8K @ 240 Hz
- Double-flow-through thermal design for sustained peak performance