Architecture NVIDIA Ampere Architecture Process Size 8nm Transistors 13.25 Billion Die Size 276 mm2 CUDA Cores 3328 Tensor Cores 104 RT Cores 26 Peak FP32 Performance 7.99 TFLOPS RT Core Performance 15.6 TFLOPS Tensor Core Performance 63.9 TFLOPS GPU Memory 6 GB GDDR6 ECC GPU Memory Clock 6001 MHz Memory Interface 192-bit Memory Bandwidth 288 GB/sec Maximum Power Consumption 70 W NVIDIA Quadro and RTX Power Guidelines System Interface PCI Express 4.0 x16 Display Connectors 4x mDP Latching Form Factor 2.713" H x 6.6" Low Profile | Dual Slot Thermal Solution Active Fansink Max Digital Resolution 2x 7680 x 4320 at 60 Hz Max Displays 4x at 5K | 5120 x 2880 at 60 Hz NVIDIA Quadro and RTX Display Resolution Support HDR Support Yes AR | VR | XR Ready Yes Quad Buffered Stereo Yes Hardware Accelerated BVH Yes NVIDIA DLSS Yes NVIDIA Mosaic, Warp and Blend Yes NVIDIA RTX Experience Yes NVIDIA RTX Desktop Manager Yes NVIDIA Broadcast Application Yes NVENC | NVDEC 1x H.264 and HVEC Encoders 1x Decode Engine Graphics APIs DirectX 12.07, Shader Model 5.17, Open GL 4.68, Vulkan 1.2 Compute APIs CUDA, DirectCompute, Open CL
