GeForce G100 OEM and GeForce RTX 4070 - video card comparison
GeForce G100 OEM
GeForce RTX 4070
Architecture
Tesla (2006−2010)
Ada Lovelace
GPU code name
G98
AD104
Market segment
Desktop
Desktop
Release date
March 2009
April 2023
Interface
PCIe 2.0 x16
PCIe 4.0 x16
Supplementary power connectors
None
1x 16-pin
Boost clock speed
-
2475 MHz
Core clock speed
540 MHz
1920 MHz
Floating-point performance
20.8 gflops
-
Manufacturing process technology
65 nm
5 nm
Number of transistors
210 million
35,800 million
Pipelines / CUDA cores
8
5888
Power consumption (TDP)
35 Watt
200 Watt
Texture fill rate
4.320
455.4
Memory type
DDR2
GDDR6X
Maximum RAM amount
256 MB
12 GB
Memory bus width
64 Bit
192 Bit
Memory clock speed
800 MHz
21000 MHz
Memory bandwidth
6.4 GB/s
504.2 GB/s
Shared memory
-
-
Display Connectors
1x DVI, 1x S-Video
1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI
-
+
DirectX
11.1 (10_0)
12 Ultimate (12_2)
CUDA
1.1
8.9
OpenCL
1.1
3.0
OpenGL
3.3
4.6
Shader Model
4.0
6.7
Vulkan
N/A
1.3