GeForce GTX 1660 Super and Tesla K20X - video card comparison

GeForce GTX 1660 Super

Tesla K20X

Architecture

Turing (2018−2021)

Kepler (2012−2018)

GPU code name

Turing TU116

GK110

Market segment

Desktop

Workstation

Release date

October 2019

November 2012

Interface

PCIe 3.0 x16

PCIe 3.0 x16

Supplementary power connectors

1x 8-pin

1x 6-pin + 1x 8-pin

Boost clock speed

1785 MHz

-

Core clock speed

1530 MHz

732 MHz

Floating-point performance

-

3,935 gflops

Manufacturing process technology

12 nm

28 nm

Number of transistors

6,600 million

7,080 million

Pipelines / CUDA cores

1408

2688

Power consumption (TDP)

125 Watt

235 Watt

Texture fill rate

157.1

164.0

Memory type

GDDR6

GDDR5

Maximum RAM amount

6 GB

6 GB

Memory bus width

192 Bit

384 Bit

Memory clock speed

14000 MHz

5200 MHz

Memory bandwidth

336.0 GB/s

249.6 GB/s

Shared memory

-

-

Display Connectors

1x DVI, 1x HDMI, 1x DisplayPort

No outputs

HDMI

+

-

HDCP

+

-

G-SYNC support

+

-

DirectX

12 (12_1)

12 (11_0)

CUDA

7.5

3.5

OpenCL

1.2

1.2

OpenGL

4.6

4.6

Shader Model

6.5

5.1

Vulkan

1.2.131

1.1.126

Ansel

+

-

NVENC

+

-