NVIDIA GeForce RTX 4070 vs NVIDIA GeForce RTX 5080 SUPER
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 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 4070 's Advantages
Lower TDP (200W vs 360W)
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
Score
Benchmark
FP32 (float)
GeForce RTX 4070
29.15 TFLOPS
GeForce RTX 5080 SUPER
+93%
56.28 TFLOPS
Graphics Card
Apr 2023
Release Date
Unknown
GeForce 40
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1920 MHz
Base Clock
2295 MHz
2475 MHz
Boost Clock
2617 MHz
1313 MHz
Memory Clock
2000 MHz
Memory
12GB
Memory Size
24GB
GDDR6X
Memory Type
GDDR7
192bit
Memory Bus
256bit
504.2GB/s
Bandwidth
1.02TB/s
Render Config
-
-
-
46
SM Count
84
5888
Shading Units
10752
184
TMUs
336
64
ROPs
112
184
Tensor Cores
336
46
RT Cores
84
128 KB (per SM)
L1 Cache
128 KB (per SM)
36 MB
L2 Cache
64 MB
-
-
-
Theoretical Performance
158.4 GPixel/s
Pixel Rate
293.1 GPixel/s
455.4 GTexel/s
Texture Rate
879.3 GTexel/s
29.15 TFLOPS
FP16 (half)
56.28 TFLOPS
29.15 TFLOPS
FP32 (float)
56.28 TFLOPS
455.4 GFLOPS
FP64 (double)
879.3 GFLOPS
Board Design
200W
TDP
360W
550 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
AD104
GPU Name
GB203
AD104-250-A1
GPU Variant
GB203-450-A1
Ada Lovelace
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
35.8 billion
Transistors
45.6 billion
295 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
6.7
Shader Model
6.8
