GeForce GTX 1650 SUPER and Tesla K40st - video card comparison

GeForce GTX 1650 SUPER

Tesla K40st

Architecture

Turing (2018−2021)

Kepler (2012−2018)

GPU code name

TU116

GK110B

Market segment

Desktop

Workstation

Release date

October 2019

November 2013

Interface

PCIe 3.0 x16

Supplementary power connectors

1x 6-pin

Boost clock speed

1725 MHz

Core clock speed

1530 MHz

575 MHz

Floating-point performance

4,291 gflops

Manufacturing process technology

12 nm

28 nm

Number of transistors

6,600 million

7,080 million

Pipelines / CUDA cores

1280

2880

Power consumption (TDP)

125 Watt

245 Watt

Texture fill rate

138.0

Memory type

GDDR6

GDDR5

Maximum RAM amount

4 GB

12 GB

Memory bus width

128 Bit

384 Bit

Memory clock speed

12000 MHz

6008 MHz

Memory bandwidth

192.0 GB/s

288.4 GB/s

Shared memory

Display Connectors

1x DVI, 1x HDMI, 1x DisplayPort

No outputs

HDMI

DirectX

12 (12_1)

12 (11_1)

CUDA

7.5

3.5

OpenCL

1.2

OpenGL

4.6

Shader Model

6.5

5.1

Vulkan

1.2.131

1.1.126

Multi Monitor

VR Ready