NVIDIA GeForce RTX 5080 SUPER vs NVIDIA GeForce RTX 4070
We compared two Desktop platform GPUs: 24GB VRAM GeForce RTX 5080 SUPER and 12GB VRAM GeForce RTX 4070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 5080 SUPER 's Advantages
Boost Clock has increased by 6% (2617MHz vs 2475MHz)
More VRAM (24GB vs 12GB)
Larger VRAM bandwidth (1.02TB/s vs 504.2GB/s)
4864 additional rendering cores
NVIDIA GeForce RTX 4070 's Advantages
Lower TDP (200W vs 360W)
Score
Benchmark
FP32 (float)
GeForce RTX 5080 SUPER
+93%
56.28 TFLOPS
GeForce RTX 4070
29.15 TFLOPS
Graphics Card
Unknown
Release Date
Apr 2023
GeForce 50
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
2295 MHz
Base Clock
1920 MHz
2617 MHz
Boost Clock
2475 MHz
2000 MHz
Memory Clock
1313 MHz
Memory
24GB
Memory Size
12GB
GDDR7
Memory Type
GDDR6X
256bit
Memory Bus
192bit
1.02TB/s
Bandwidth
504.2GB/s
Render Config
-
-
-
84
SM Count
46
10752
Shading Units
5888
336
TMUs
184
112
ROPs
64
336
Tensor Cores
184
84
RT Cores
46
128 KB (per SM)
L1 Cache
128 KB (per SM)
64 MB
L2 Cache
36 MB
-
-
-
Theoretical Performance
293.1 GPixel/s
Pixel Rate
158.4 GPixel/s
879.3 GTexel/s
Texture Rate
455.4 GTexel/s
56.28 TFLOPS
FP16 (half)
29.15 TFLOPS
56.28 TFLOPS
FP32 (float)
29.15 TFLOPS
879.3 GFLOPS
FP64 (double)
455.4 GFLOPS
Board Design
360W
TDP
200W
750 W
Suggested PSU
550 W
1x HDMI 2.1b
3x DisplayPort 2.1b
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 16-pin
Power Connectors
1x 16-pin
Graphics Processor
GB203
GPU Name
AD104
GB203-450-A1
GPU Variant
AD104-250-A1
Blackwell 2.0
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
45.6 billion
Transistors
35.8 billion
378 mm²
Die Size
295 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.4
Vulkan
1.3
12.0
CUDA
8.9
6.8
Shader Model
6.7
