GeForce GTX 970 vs GeForce RTX 4090
We compared two Desktop platform GPUs: 4GB VRAM GeForce GTX 970 and 24GB VRAM GeForce RTX 4090 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce GTX 970 's Advantages
Lower TDP (148W vs 450W)
GeForce RTX 4090 's Advantages
Released 8 years late
Boost Clock has increased by 114% (2520MHz vs 1178MHz)
More VRAM (24GB vs 4GB)
Larger VRAM bandwidth (1.01TB/s vs 224.4GB/s)
14720 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 970
3920
GeForce RTX 4090
+2006%
82580
3DMark Time Spy
GeForce GTX 970
3646
GeForce RTX 4090
+896%
36328
3DMark Time Spy Extreme
GeForce GTX 970
1683
GeForce RTX 4090
+1056%
19460
Blender
GeForce GTX 970
305
GeForce RTX 4090
+4026%
12586
OctaneBench
GeForce GTX 970
77
GeForce RTX 4090
+1554%
1274
Shadow of the Tomb Raider 2160p
GeForce GTX 970
15
GeForce RTX 4090
+1133%
185
Shadow of the Tomb Raider 1440p
GeForce GTX 970
30
GeForce RTX 4090
+833%
280
Shadow of the Tomb Raider 1080p
GeForce GTX 970
40
GeForce RTX 4090
+660%
304
GTA 5 2160p
GeForce GTX 970
42
GeForce RTX 4090
+292%
165
GTA 5 1440p
GeForce GTX 970
44
GeForce RTX 4090
+320%
185
GTA 5 1080p
GeForce GTX 970
98
GeForce RTX 4090
+89%
186
Graphics Card
Sep 2014
Release Date
Sep 2022
GeForce 900
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1050 MHz
Base Clock
2235 MHz
1178 MHz
Boost Clock
2520 MHz
1753 MHz
Memory Clock
1313 MHz
Memory
4GB
Memory Size
24GB
GDDR5
Memory Type
GDDR6X
256bit
Memory Bus
384bit
224.4GB/s
Bandwidth
1.01TB/s
Render Config
-
SM Count
128
1664
Shading Units
16384
104
TMUs
512
56
ROPs
176
-
Tensor Cores
512
-
RT Cores
128
48 KB (per SMM)
L1 Cache
128 KB (per SM)
2 MB
L2 Cache
72 MB
Theoretical Performance
65.97 GPixel/s
Pixel Rate
443.5 GPixel/s
122.5 GTexel/s
Texture Rate
1290 GTexel/s
-
FP16 (half)
82.58 TFLOPS
3.920 TFLOPS
FP32 (float)
82.58 TFLOPS
122.5 GFLOPS
FP64 (double)
1290 GFLOPS
Board Design
148W
TDP
450W
300 W
Suggested PSU
850 W
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
2x 6-pin
Power Connectors
1x 16-pin
Graphics Processor
GM204
GPU Name
AD102
GM204-200-A1
GPU Variant
AD102-300-A1
Maxwell 2.0
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
28 nm
Process Size
5 nm
5.2 billion
Transistors
76.3 billion
398 mm²
Die Size
609 mm²
Graphics Features
12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
5.2
CUDA
8.9
6.4
Shader Model
6.8
