Tesla V100 PCIe and GeForce RTX 2050 Max-Q - video card comparison

Tesla V100 PCIe

GeForce RTX 2050 Max-Q

Architecture

Volta (2017−2020)

Ampere (2020−2022)

GPU code name

GV100

GA107

Market segment

Workstation

Desktop

Release date

June 2017

December 2021

Interface

PCIe 3.0 x16

PCIe 3.0 x8

Supplementary power connectors

2x 8-pin

None

Boost clock speed

1380 MHz

1155 MHz

Core clock speed

1246 MHz

Floating-point performance

14,131 gflops

Manufacturing process technology

12 nm

8 nm

Number of transistors

21,100 million

Pipelines / CUDA cores

5120

2048

Power consumption (TDP)

250 Watt

30 Watt

Texture fill rate

441.6

73.92

Memory type

HBM2

GDDR6

Maximum RAM amount

16 GB

4 GB

Memory bus width

4096 Bit

64 Bit

Memory clock speed

1758 MHz

12 GB/s

Memory bandwidth

900.1 GB/s

96 GB/s

Display Connectors

No outputs

1x DVI, 1x HDMI 2.1, 2x DisplayPort 1.4a

HDMI

DirectX

12.0

12 Ultimate (12_2)

CUDA

7.0

8.6

OpenCL

2.0

3.0

OpenGL

4.6

Shader Model

5.0

6.7

Vulkan

1.3