Opis artikla
CUDA Cores 10752
NVIDIA RT Cores 84
NVIDIA Tensor Cores 336
GPU Memory 48 GB GDDR6 with ECC
Peak FP32 Performance 38.7 TFLOPS (Boost Clocks)
RT Core Performance 75.6 TFLOPS (Boost clocks)
Tensor Core Performance 309.7 TFLOPS (Boost Clocks)
Multi-GPU Scalability NVLink
NVLink Bandwidth 112,5 GB/Sec
Memory Bandwidth 768 GB/s
System Interface PCI Express 4.0 x16
Maximum Power Consumption 300 W
Energy Star Enabling Yes
Thermal Solution Ultra-quiet active fansink
Form Factor 111.8 mm H x 266.7 mm L, Dual Slot
Display Connectors DisplayPort 1.4 (4)
DisplayPort with Audio Yes
DVI-D Single-Link Connector Yes, via optional adapter
HDMI Support Yes, via included adapter
Number of Displays Supported 4
Maximum DP 1.4 Resolution HDR 7680 x 4320 at 60 Hz
5K Display Support HDR 5120 x 2880 at 60 Hz
4K Display Support HDR 4096 x 2160 or 3840 x 2160 at 120 Hz
Maximum DVI-D DL Resolution 2560 x 1600 at 60 Hz via 3rd party adapter
Maximum DVI-D SL Resolution 1920 x 1200 at 60 Hz via optional adapter
HDCP Support 2.2
Professional 3D Support Via optional Stereo Connector Bracket
Quadro Sync II Compatible Yes (Frame Lock and Genlock)
NVIDIA GPU Direct Compatible Yes
Graph APIs Shader Model 5.1, OpenGL 4.5, DirectX 12.0, Vulkan 1.0
Compute APIs CUDA, DirectCompute, OpenCL
NVIEW Yes
NVIDIA MOSAIC Yes
