NVIDIA Quadro RTX 8000 Passive Full Specs
4,608 Shaders 1.62GHz |
48GB GDDR6672GB/s |
·· 14.93 TFLOPS |
Form Factor PCIe Card |
Power Connectors 1x 8-Pin 1x 6-Pin |
Clock Speed ··· |
Peak OPS 477.8 TOPSINT4 Tensor |
Tensor FP16-16 119.4 TFLOPSTensor FP16-32 59.72 TFLOPS |
Tensor BF16 59.72 TFLOPS |
Tensor TF32 59.72 TFLOPS |
FP32 14.93 TFLOPS |
FP64 466.6 GFLOPS |
Tensor INT4 477.8 TOPS |
Tensor INT8 238.9 TOPS |
Ray 45.03 TOPS |
Pixel Rate 155.5 GPixel/s |
Texture Rate 466.6 GTexel/s |
Shaders 4,608 Shaders |
TMUs 288 TMUs |
ROPs 96 ROPs |
Tensor Cores 576 T-Cores |
RT Cores 72 RT-Cores |
SMs 72 SMs |
Base Clock 1.23GHz |
Boost Clock 1.62GHz |
L2 Cache 6.1MB shared |
48GB GDDR6 |
Memory Bus 384-bit |
Memory Speed 14GT/s |
Memory Bandwidth 672GB/s |
ECC Yes |
Multi-Monitor 4 |
HDCP HDCP 2.2 |
Encoder Model NVENC 7 |
Decoder Model NVDEC 4 |
Form Factor PCIe Card |
PCIe 2-Slots |
Height 111 mm (4.37")Width 267 mm (10.51")Depth 40 mm (1.57") |
Cooling Passive |
Power Connectors 1x 8-Pin, 1x 6-Pin |
Manufacturer |
Chip Designer |
Architecture |
Family |
Branding  |
Codename NV162 |
Chip Variant TU102-300A-K1-A1 |
Market Segment Workstation |
Release Date Aug 13, 2018 |
Foundry TSMC |
Fabrication Node 12FFN |
Die Size 754mm² |
Transistor Count 18.6 Billion |
Transistor Density 24.67 MTr/mm² |
No images available
