Fire GL1 and GeForce RTX 3070 Max-Q - video card comparison

Fire GL1

GeForce RTX 3070 Max-Q

Architecture

IBM (1999−2001)

Ampere (2020−2022)

GPU code name

IBM

GN20-E5 GA104

Market segment

Desktop

Laptop

Release date

March 1999

January 2021

Interface

AGP 2x

PCIe 4.0 x16

Supplementary power connectors

None

Boost clock speed

1290 MHz

Core clock speed

45 MHz

Manufacturing process technology

250 nm

8 nm

Number of transistors

17,400 million

Pipelines / CUDA cores

5120

Power consumption (TDP)

80 Watt

Texture fill rate

0.05

237.4

Memory type

SDR

GDDR6

Maximum RAM amount

32 MB

8 GB

Memory bus width

256 Bit

Memory clock speed

100 MHz

12 GB/s

Memory bandwidth

3.2 GB/s

320.0 GB/s

Shared memory

Display Connectors

1x VGA

1x HDMI, 3x DisplayPort

HDMI

DirectX

6.0

12 Ultimate (12_2)

CUDA

8.6

OpenCL

N/A

2.0

OpenGL

1.2

4.6

Shader Model

6.5

Vulkan

N/A

1.2