Organizations and enterprises of all sizes are entering a new era of computing. An era where deep learning, visualization, and virtualization sit side-by-side in the data center and are used by scientists, researchers, designers, renderers, engineers, and knowledge workers alike. GPUs powered by the revolutionary NVIDIA Pascal architecture provide the computational engine for this new era, enabling amazing user experiences by accelerating both compute and graphics virtualization at scale. The NVIDIA Tesla P6 is designed for blade servers and supports multiple data center workloads, including deep learning, HPC, and graphics virtualization. It delivers higher graphics performance, improved energy efficiency, and up to twice the frame buffer compared to the NVIDIA Tesla M6. It also comes in an MXM form factor running at less than 90 W for high-density data centers with blade servers and converged infrastructure. Plus, it can support up to 16 concurrent users (1 GB profile).