Quadro RTX 4000 and Tesla M2070 - video card comparison

Quadro RTX 4000

Tesla M2070

Architecture

Turing (2018−2021)

Fermi (2010−2014)

GPU code name

TU104

GF100

Market segment

Workstation

Workstation

Release date

November 2018

July 2011

Interface

PCIe 3.0 x16

PCIe 2.0 x16

Supplementary power connectors

1x 8-pin

1x 6-pin + 1x 8-pin

Boost clock speed

1545 MHz

-

Core clock speed

1005 MHz

574 MHz

Floating-point performance

-

1,030.4 gflops

Manufacturing process technology

12 nm

40 nm

Number of transistors

13,600 million

3,100 million

Pipelines / CUDA cores

2304

448

Power consumption (TDP)

160 Watt

225 Watt

Texture fill rate

222.5

32.14

Memory type

GDDR6

GDDR5

Maximum RAM amount

8 GB

6 GB

Memory bus width

256 Bit

384 Bit

Memory clock speed

13000 MHz

3132 MHz

Memory bandwidth

416.0 GB/s

150.3 GB/s

Display Connectors

3x DisplayPort, 1x USB Type-C

No outputs

DirectX

12 Ultimate (12_1)

12 (11_0)

CUDA

7.5

2.0

OpenCL

1.2

1.1

OpenGL

4.6

4.6

Shader Model

6.5

5.1

Vulkan

1.2.131

N/A