✔ 4,608 NVIDIA® CUDA® Cores
✔ 576 NVIDIA® Tensor Cores
✔ 72 NVIDIA® RT Cores
✔ 48GB GDDR6 Memory
✔ Up to 672GB/s Memory Bandwidth
✔ 84T RTX-OPS
✔ 10 Giga Rays/s Rays Cast
✔ 16.3 TFLOPS FP32 Performance
✔ 32.6 TFLOPS FP16 Performance
✔ 65.8 TOPS INT8 Performance
✔ 130.5 TFLOPS of Tensor Operation
✔ Max. Power Consumption: 295W
✔ 4x DisplayPort 1.4
✔ 1x VirtualLink
✔ Warranty: 1 year manufacturer replacement or repair
Specification | Detail |
|---|---|
GPU Architecture | Turing |
CUDA Parallel Processing cores | 4608 |
NVIDIA Tensor Cores | 576 |
NVIDIA RT Cores | 72 |
Frame Buffer Memory | 48 GB GDDR6 |
RTX-OPS | 84T |
Rays Cast | 10 Giga Rays/Sec |
Peak Single Precision (FP32) Performance | 16.3 TFLOPS |
Peak Half Precision (FP16) Performance | 32.6 TFLOPS |
Peak Integer Operation (INT8) Performance | 65.2 TOPS |
Deep Learning TeraFLOPS^1 | 130.5 Tensor TFLOPS |
Memory Interface | 384-bit |
Memory Bandwidth | 672 GB/s |
Max Power Consumption | 295 W |
Graphics Bus | PCI Express 3.0 x16 |
Display Connectors | DP 1.4 (4) + VirtualLink (1) |
Form Factor | 4.4” H x 10.5” L Dual Slot |
Product Weight | 1.002 kg |
Thermal Solution | Active |
Power Connector | 1x 8-pin & 1x 6-pin |
Frame lock | Compatible (with Quadro Sync II) |
NVLink Interconnect | 100 GB/s |