CUDA Cores 6912
Streaming Multiprocessors 108
GPU Memory 80GB HBM2e | ECC on by default
Memory Interface 5120-bit
Memory Bandwidth 1555GB/s
NVLink 2-way | Standard or Wide Slot Spacing
MIG (Multi-Instance GPU Support) Yes | Up to 7 GPU Instances
FP64 9.7 TFLOPS
FP64 Tensor Core 156 TFLOPS | 312 TFLOPS Sparsity
FP32 19.5 TFLOPS
TF32 Tensor Core 156 TFLOPS | 312 TFLOPS Sparsity
FP16 Tensor Core 312 TFLOPS | 624 TFLOPS Sparsity
INT8 Tensor Core 624 TOPS | 1248 TOPS Sparsity
INT4 Tensor Core 1248 TOPS | 2496 TOPS Sparsity
Thermal Solution Liquid Cooled
vGPU Support NVIDIA AI Enterprise
System Interface PCI Express 4.0 x16
Total Board Power 300W
9001-2015-E.PNG)
