Power and Performance in a Small Form Factor The NVIDIA® T400, built on the NVIDIA Turing™ GPU architecture, delivers amazing performance and capabilities to power a range of professional workflows. Featuring 384 CUDA cores and 2GB or 4GB of GDDR6 memory, the T400 packs power and performance in a small form factor so professionals can tackle a range of multi-app workflows with ease. Native support for up to three 5K displays gives you the expansive visual workspace to view your work in stunning detail. NVIDIA RTX™ professional graphics cards are certified with a broad range of professional applications, tested by leading independent software vendors (ISVs) and workstation manufacturers, and backed by a global team of support specialists. Get the peace of mind you need to focus on what matters most with the premier visual computing platform for mission-critical business. Features • Three Mini DisplayPort 1.4 connectors with latching mechanism. • DisplayPort with audio. • NVIDIA RTX Desktop Manager software. • NVIDIA RTX Experience. • NVIDIA Mosaic technology. • HDCP 2.2 support. Key Specifications Graphics Chipset     Edition    NVIDIA T400 Manufacturing process    12 nm Microarchitecture    Turing GPU Name     Cores & Clocks NVIDIA CUDA Cores    384 Core Clock     Boost Clock     Video Memory (VRAM) Memory Size    4 GB Memory Type    GDDR6 Memory Clock     Memory Bit Rate    64 Bit Memory Bandwidth    80 GB/s ECC Technology    No Cooling Cooling    Single Fan (1) I/O & Connectivity Interface    PCIe 3.0 (x16) Interface Bandwidth     Graphics Output    3 x Mini DisplayPort 1.4 Visuals Multi GPU Support     NVLink Support    N/A Total NVLink Bandwidth    N/A Microsoft DirectX Support    12 API HDCP Ready    Yes Multi Monitor Support    3 Displays Concurent Users    N/A H.264 1080p30 Streams    N/A Maximum Digital Resolution    5120x2880 @ 60Hz Maximum VGA Resolution     Supported Graphics APIs     DirectX 12.0 OpenGL 4.6 Shader Model 5.1 Vulkan 1.2 Compute Performance Supported Compute APIs     CUDA DirectCompute OpenCL Single Precision (FP32) Processing    Yes Single Precision (FP32) Performance    1.09 teraFLOPS Double Precision (FP64) Processing    No Double Precision (FP64) Performance     Tensor Processing    No Deep Learning (Tensor) Performance     NVIDIA Tensor Cores     Integer Operations (INT8)     Ray-Tracing NVIDIA RT Cores     RTX-OPS     Rays Cast     Power & Thermals Graphics Card Power Connectors     Board Power    30 W Minimum Recommended PSU     Maximum GPU Temperature     Physical Form Factor    Single Slot Low Profile Compatible    Yes Low Profile Support     Dimensions     Package Type    OEM