GeForce GTX 970 and GeForce RTX 4090 - video card comparison
Passmark - benchmark score GeForce GTX 970 vs GeForce RTX 4090
GeForce GTX 970
9932
GeForce RTX 4090
39777
GeForce GTX 970
GeForce RTX 4090
Architecture
Maxwell (2014−2018)
Ada Lovelace
GPU code name
GM204
AD102-300-A1
Market segment
Desktop
Desktop
Release date
September 2014
September 2022
Bus support
PCI Express 3.0
-
Interface
PCIe 3.0 x16
PCIe 4.0 x16
Recommended system power (PSU)
500 Watt
-
Supplementary power connectors
2x 6-pins
1x 16-pin
SLI options
+
-
Boost clock speed
1178 MHz
2520 MHz
Core clock speed
1050 MHz
2235 MHz
CUDA cores
1664
-
Floating-point performance
3,920 gflops
-
Manufacturing process technology
28 nm
5 nm
Number of transistors
5,200 million
76,300 million
Pipelines / CUDA cores
1664
16384
Power consumption (TDP)
145 Watt
450 Watt
Maximum GPU temperature
98 °C
-
Texture fill rate
109 billion/sec
1,290
Memory type
GDDR5
GDDR6X
Maximum RAM amount
4 GB
24 GB
Memory bus width
256 Bit
384 Bit
Memory clock speed
7.0 GB/s
21000 MHz
Memory bandwidth
224 GB/s
1,008 GB/s
Shared memory
-
-
Display Connectors
Dual Link DVI-I, HDMI 2.0, 3x DisplayPort 1.2
1x HDMI 2.1, 3x DisplayPort 1.4a
Multi monitor support
4 displays
-
HDMI
+
+
HDCP
+
-
Maximum VGA resolution
2048x1536
-
G-SYNC support
+
-
Audio input for HDMI
Internal
-
DirectX
12 (12_1)
12 Ultimate (12_2)
CUDA
+
8.9
OpenCL
1.2
3.0
OpenGL
4.4
4.6
Shader Model
6.4
6.6
Vulkan
1.1.126
1.3
GameStream
+
-
GameWorks
+
-
GeForce ShadowPlay
+
-
GPU Boost
2.0
-