Architecture	Ampere
Process Size	8nm | Samsung
Transistors	13.25 Billion
Die Size	276mm2
CUDA Cores	3328
Tensor Cores	104
RT Cores	26
Peak FP32 Performance	8.0 TFLOPS
RT Core Performance	15.6 TLOPS
Tensor Core Performance	63.9 TFLOPS
GPU Memory	12GB GDDR6 with ECC
GPU Memory Clock	6001 MHz
Memory Inferface	192-bit
Memory Bandwidth	288 GB/s
Max Power Consumption	70 W
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	4
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