GeForce RTX 4090 and GeForce FX 5700 Engineering Sample - video card comparison

GeForce RTX 4090

GeForce FX 5700 Engineering Sample

Architecture

Ada Lovelace

Rankine (2003−2005)

GPU code name

AD102-300-A1

NV36S

Market segment

Desktop

Release date

September 2022

August 2003

Interface

PCIe 4.0 x16

AGP 8x

Supplementary power connectors

1x 16-pin

1x Molex

Boost clock speed

2520 MHz

Core clock speed

2235 MHz

425 MHz

Manufacturing process technology

5 nm

130 nm

Number of transistors

76,300 million

82 million

Pipelines / CUDA cores

16384

Power consumption (TDP)

450 Watt

25 Watt

Texture fill rate

1,290

1.700

Memory type

GDDR6X

DDR

Maximum RAM amount

24 GB

128 MB

Memory bus width

384 Bit

128 Bit

Memory clock speed

21000 MHz

500 MBps

Memory bandwidth

1,008 GB/s

8 GB/s

Shared memory

Display Connectors

1x HDMI 2.1, 3x DisplayPort 1.4a

1x DVI, 1x VGA, 1x S-Video

HDMI

DirectX

12 Ultimate (12_2)

9.0a

CUDA

8.9

OpenCL

3.0

N/A

OpenGL

4.6

1.5 (full) Shader Model6.6-

Vulkan

1.3

N/A