NVIDIA GeForce RTX 4090 vs NVIDIA GeForce RTX 5080 SUPER
We compared two Desktop platform GPUs: 24GB VRAM GeForce RTX 4090 and 24GB VRAM GeForce RTX 5080 SUPER to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4090 's Advantages
5632 additional rendering cores
NVIDIA GeForce RTX 5080 SUPER 's Advantages
Boost Clock has increased by 4% (2617MHz vs 2520MHz)
Larger VRAM bandwidth (1.02TB/s vs 1.01TB/s)
Lower TDP (360W vs 450W)
Score
Benchmark
FP32 (float)
GeForce RTX 4090
+46%
82.58 TFLOPS
GeForce RTX 5080 SUPER
56.28 TFLOPS
Graphics Card
Sep 2022
Release Date
Unknown
GeForce 40
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
2235 MHz
Base Clock
2295 MHz
2520 MHz
Boost Clock
2617 MHz
1313 MHz
Memory Clock
2000 MHz
Memory
24GB
Memory Size
24GB
GDDR6X
Memory Type
GDDR7
384bit
Memory Bus
256bit
1.01TB/s
Bandwidth
1.02TB/s
Render Config
-
-
-
128
SM Count
84
16384
Shading Units
10752
512
TMUs
336
176
ROPs
112
512
Tensor Cores
336
128
RT Cores
84
128 KB (per SM)
L1 Cache
128 KB (per SM)
72 MB
L2 Cache
64 MB
-
-
-
Theoretical Performance
443.5 GPixel/s
Pixel Rate
293.1 GPixel/s
1290 GTexel/s
Texture Rate
879.3 GTexel/s
82.58 TFLOPS
FP16 (half)
56.28 TFLOPS
82.58 TFLOPS
FP32 (float)
56.28 TFLOPS
1290 GFLOPS
FP64 (double)
879.3 GFLOPS
Board Design
450W
TDP
360W
850 W
Suggested PSU
750 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1b
1x 16-pin
Power Connectors
1x 16-pin
Graphics Processor
AD102
GPU Name
GB203
AD102-300-A1
GPU Variant
GB203-450-A1
Ada Lovelace
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
76.3 billion
Transistors
45.6 billion
609 mm²
Die Size
378 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.4
8.9
CUDA
12.0
6.8
Shader Model
6.8
