Ampere Architecture
CUDA Cores 10,752
Tensor Cores 336
RT Cores 84
Single-Precision Performance 38.7 TFLOPS
RT Core Performance 75.6 TFLOPS
Tensor Performance 309.7 TFLOPS
GPU Memory 48 GB GDDR6 with ECC
Memory Interface 384-bit
Memory Bandwidth 768 GB/sec
System Interface PCI Express 4.0 x16
Display Connectors 4x DisplayPort 1.4a
Maximum Power Consumption 300W
Ampere Architecture
CUDA Cores 10,240
Tensor Cores 320
RT Cores 80
Single Precision Performance 34.1 TFLOPS
RT Core Performance 66.6 TFLOPS
Tensor Performance 272.8 TFLOPS
GPU Memory 24GB GDDR6 with ECC
Memory Interface 320-bit
Memory Bandwidth 768 GB/sec
System Interface PCI Express 4.0 x16
Display Connectors 4x DisplayPort 1.4a
Maximum Power Consumption 230 W
Ampere Architecture
CUDA Cores 8,192
Tensor Cores 256
RT Cores 64
Single Precision Performance 27.8 TFLOPS
RT Core Performance 54.2 TFLOPS
Tensor Performance 222.2 TFLOPS
GPU Memory 24 GB GDDR6 with ECC
Memory Interface 384-bit
Memory Bandwidth 768 GB/sec
System Interface PCI Express 4.0 x16
Display Connectors 4x DisplayPort 1.4a
Maximum Power Consumption 230 W
Ampere Architecture
CUDA Cores 7,168
Tensor Cores 224
RT Cores 56
Single Precision Performance 23.7 TFLOPS
RT Core Performance 46.2 TFLOPS
Tensor Performance 189.2 TFLOPS
GPU Memory 20GB GDDR6 with ECC
Memory Interface 320-bit
Memory Bandwidth 640 GB/sec
System Interface PCI Express 4.0 x16
Display Connectors 4x DisplayPort 1.4
Maximum Power Consumption 200 W
Ampere Architecture
CUDA Cores 6,144
Tensor Cores 192
RT Cores 48
Single Precision Performance 19.2 TFLOPS
RT Core Performance 37.4 TFLOPS
Tensor Performance 153.4 TFLOPS
GPU Memory 16 GB GDDR6 with ECC
Memory Interface 256-bit
Memory Bandwidth 448 GB/sec
System Interface PCI Express 4.0 x16
Display Connectors 4x DisplayPort 1.4a
Maximum Power Consumption 140 W
Ampere Architecture
CUDA Cores 3,328
Tensor Cores 104
RT Cores 26
Single-Precision Performance 8.0 TFLOPS
RT Core Performance 15.6 TFLOPS
Tensor Performance 63.9 TFLOPS
GPU Memory 6GB GDDR6 with ECC
Memory Interface 192-bit
Memory Bandwidth 288 GB/s
System Interface PCI Express 4.0 x16
Display Connectors 4x mDisplayPort 1.4a
Maximum Power Consumption 70W
Turing Architecture
CUDA Cores 4,608
RT Cores72
Tensor Cores 576
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 INT8 Performance 206.1 TOPS
Deep Learning TFLOPS 130.5 Tensor TFLOPS
GPU Memory 48 GB GDDR6 with ECC
Memory Bandwidth 672 GB/Sec
PCI Express 3.0 x16
DisplayPort 1.4 (4) + VirtualLink
Turing Architecture
CUDA Cores 4,608
RT Cores 72
Tensor Cores 576
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 INT8 Performance 206.1 TOPS
Deep Learning TFLOPS 130.5 Tensor TFLOPS
GPU Memory 24 GB GDDR6 with ECC
Memory Bandwidth 624 GB/Sec
PCI Express 3.0 x16
DisplayPort 1.4 (4), 1x USB-C
Turing Architecture
CUDA Cores 3,072
RT Cores 48
Tensor Cores 384
RTX-OPS 62T
Rays Cast 8 Giga Rays/Sec
Peak Single Precision FP32 Performance 11.2 TFLOPS
Peak Half Precision FP16 Performance 22.3 TFLOPS
Peak INT8 Performance 178.4 TOPS
Deep Learning TFLOPS 89.2 Tensor TFLOPS
GPU Memory 16 GB GDDR6 with ECC
Memory Bandwidth 448 GB/Sec
PCI Express 3.0 x16
DP 1.4 (4), 1x USB-C
Turing Architecture
CUDA Cores 2,304
RT Cores 36
Tensor Cores 288
RTX-OPS 43T
Rays Cast 6.0 Giga Rays/Sec
Peak Single Precision FP32 Performance 7.1 TFLOPS
Peak Half Precision FP16 Performance 14.2 TFLOPS
Peak INT8 Performance 28.5 TOPS
Deep Learning TFLOPS 57.0 Tensor TFLOPS
GPU Memory 8 GB GDDR6
Memory Bandwidth 416 GB/Sec
PCI Express 3.0 x16
DisplayPort 1.4 (3), 1x USB-C
Volta Architecture
CUDA Cores 5,120
Tensor Cores 640
Peak Double Precision FP64 Performance 7.4 TFLOPS
Peak Single Precision FP32 Performance 14.8 TFLOPS
Peak Half Precision FP16 Performance 29.6 TFLOPS
Peak Integer Operation (INT8) Performance 59.3 TOPS
Deep Learning TFLOPS 118.5 TFLOPS
GPU Memory 32 GB HBM2
Memory Interface 4096-bit
Memory Bandwidth 870 GB/s
System Interface PCI Express 3.0 x16
Display Connectors DP 1.4 (4)
2-Way 2-Slot Spacing
UP To 200 GB/s Bidirectional with 2 Bridges
Supported Graphics Cards :
NVIDIA GV100
Turing Architecture
CUDA Cores 896
Peak FP32 Performance 2.50 TFLOPS
GPU Memory 4 GB / 8 GB GDDR6
Memory Interface 128-bit
Memory Bandwidth 160 GB/s
Max Power Consumption 50 W
System Interface PCI Express 3.0 x16
Display Connectors 4x mDP
Form Factor Low-Profile Single Slot
Thermal Solution Active Fansink
Turing Architecture
CUDA Cores 640
Peak FP32 Performance 1.709 TFLOPS
GPU Memory 4 GB GDDR6
Memory Interface 128-bit
Memory Bandwidth 160 GB/s
Max Power Consumption 40 W
System Interface PCI Express 3.0 x16
Display Connectors 4x mDP
Form Factor Low-Profile Single Slot
Thermal Solution Active Fansink
Turing Architecture
CUDA Cores 384
Peak FP32 Performance 1.094 TFLOPS
GPU Memory 2 GB / 4 GB GDDR6
Memory Interface 64-bit
Memory Bandwidth 80 GB/s
Max Power Consumption 30 W
System Interface PCI Express 3.0 x16
Display Connectors 3x mDP
Form Factor Low-Profile Single Slot
Thermal Solution Active Fansink
Pascal Architecture
CUDA Cores 1,280
Peak Single Precision
FP32 Performance 3.8 TFLOPS
GPU Memory 5 GB GDDR5X
Memory Interface 160-bit
Memory Bandwidth Up to 200 GB/s
System Interface PCI Express 3.0 x16
Display Connectors DP 1.4 (4)
Pascal Architecture
CUDA Cores 640
Peak Single Precision FP32
Performance 1.894 TFLOPS
GPU Memory 4 GB GDDR5
Memory Interface 128-bit
Memory Bandwidth 82 GB/s
System Interface PCI Express 3.0 x16
Display Connectors mDP 1.4 (4)