GeForce GTX 1650 SUPER vs GeForce RTX 4090
We compared two Desktop platform GPUs: 4GB VRAM GeForce GTX 1650 SUPER 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 1650 SUPER 's Advantages
Lower TDP (100W vs 450W)
GeForce RTX 4090 's Advantages
Released 2 years and 10 months late
Boost Clock has increased by 46% (2520MHz vs 1725MHz)
More VRAM (24GB vs 4GB)
Larger VRAM bandwidth (1.01TB/s vs 192.0GB/s)
15104 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 1650 SUPER
4416
GeForce RTX 4090
+1770%
82580
3DMark Time Spy
GeForce GTX 1650 SUPER
4694
GeForce RTX 4090
+673%
36328
3DMark Time Spy Extreme
GeForce GTX 1650 SUPER
2072
GeForce RTX 4090
+839%
19460
Blender
GeForce GTX 1650 SUPER
596
GeForce RTX 4090
+2011%
12586
OctaneBench
GeForce GTX 1650 SUPER
93
GeForce RTX 4090
+1269%
1274
Shadow of the Tomb Raider 2160p
GeForce GTX 1650 SUPER
19
GeForce RTX 4090
+873%
185
Shadow of the Tomb Raider 1440p
GeForce GTX 1650 SUPER
40
GeForce RTX 4090
+600%
280
Shadow of the Tomb Raider 1080p
GeForce GTX 1650 SUPER
64
GeForce RTX 4090
+375%
304
Battlefield 5 2160p
GeForce GTX 1650 SUPER
33
GeForce RTX 4090
+463%
186
Battlefield 5 1440p
GeForce GTX 1650 SUPER
63
GeForce RTX 4090
+222%
203
Battlefield 5 1080p
GeForce GTX 1650 SUPER
82
GeForce RTX 4090
+159%
213
GTA 5 2160p
GeForce GTX 1650 SUPER
46
GeForce RTX 4090
+258%
165
GTA 5 1440p
GeForce GTX 1650 SUPER
46
GeForce RTX 4090
+302%
185
GTA 5 1080p
GeForce GTX 1650 SUPER
142
GeForce RTX 4090
+30%
186
Graphics Card
Nov 2019
Release Date
Sep 2022
GeForce 16
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1530 MHz
Base Clock
2235 MHz
1725 MHz
Boost Clock
2520 MHz
1500 MHz
Memory Clock
1313 MHz
Memory
4GB
Memory Size
24GB
GDDR6
Memory Type
GDDR6X
128bit
Memory Bus
384bit
192.0GB/s
Bandwidth
1.01TB/s
Render Config
20
SM Count
128
1280
Shading Units
16384
80
TMUs
512
32
ROPs
176
-
Tensor Cores
512
-
RT Cores
128
64 KB (per SM)
L1 Cache
128 KB (per SM)
1024 KB
L2 Cache
72 MB
Theoretical Performance
55.20 GPixel/s
Pixel Rate
443.5 GPixel/s
138.0 GTexel/s
Texture Rate
1290 GTexel/s
8.832 TFLOPS
FP16 (half)
82.58 TFLOPS
4.416 TFLOPS
FP32 (float)
82.58 TFLOPS
138.0 GFLOPS
FP64 (double)
1290 GFLOPS
Board Design
100W
TDP
450W
300 W
Suggested PSU
850 W
1x DVI
1x HDMI 2.0
1x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 6-pin
Power Connectors
1x 16-pin
Graphics Processor
TU116
GPU Name
AD102
TU116-250-KA-A1
GPU Variant
AD102-300-A1
Turing
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
12 nm
Process Size
5 nm
6.6 billion
Transistors
76.3 billion
284 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
7.5
CUDA
8.9
6.6
Shader Model
6.8
