NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 4070
We compared two Desktop platform GPUs: 16GB VRAM GeForce RTX 4080 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 4080 SUPER 's Advantages
Released 9 months late
Boost Clock has increased by 3% (2550MHz vs 2475MHz)
More VRAM (16GB vs 12GB)
Larger VRAM bandwidth (736.3GB/s vs 504.2GB/s)
4352 additional rendering cores
NVIDIA GeForce RTX 4070 's Advantages
Lower TDP (200W vs 320W)
Score
Benchmark
FP32 (float)
GeForce RTX 4080 SUPER
+79%
52.22 TFLOPS
GeForce RTX 4070
29.15 TFLOPS
3DMark Time Spy
GeForce RTX 4080 SUPER
+58%
28304
GeForce RTX 4070
17887
3DMark Time Spy Extreme
GeForce RTX 4080 SUPER
+77%
14052
GeForce RTX 4070
7907
3DMark Speed Way
GeForce RTX 4080 SUPER
+35%
7450
GeForce RTX 4070
5508
Blender
GeForce RTX 4080 SUPER
+58%
9232
GeForce RTX 4070
5818
OctaneBench
GeForce RTX 4080 SUPER
+50%
964
GeForce RTX 4070
640
Shadow of the Tomb Raider 2160p
GeForce RTX 4080 SUPER
+68%
138
GeForce RTX 4070
82
Shadow of the Tomb Raider 1440p
GeForce RTX 4080 SUPER
+58%
254
GeForce RTX 4070
160
Shadow of the Tomb Raider 1080p
GeForce RTX 4080 SUPER
+17%
300
GeForce RTX 4070
256
Cyberpunk 2077 2160p
GeForce RTX 4080 SUPER
+38%
75
GeForce RTX 4070
54
Cyberpunk 2077 1440p
GeForce RTX 4080 SUPER
+39%
130
GeForce RTX 4070
93
Cyberpunk 2077 1080p
GeForce RTX 4080 SUPER
+42%
185
GeForce RTX 4070
130
Battlefield 5 2160p
GeForce RTX 4080 SUPER
+61%
158
GeForce RTX 4070
98
Battlefield 5 1440p
GeForce RTX 4080 SUPER
+16%
200
GeForce RTX 4070
172
Battlefield 5 1080p
GeForce RTX 4080 SUPER
200
GeForce RTX 4070
200
GTA 5 2160p
GeForce RTX 4080 SUPER
+27%
168
GeForce RTX 4070
132
GTA 5 1440p
GeForce RTX 4080 SUPER
+25%
180
GeForce RTX 4070
144
GTA 5 1080p
GeForce RTX 4080 SUPER
190
GeForce RTX 4070
190
Graphics Card
Jan 2024
Release Date
Apr 2023
GeForce 40
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
2295 MHz
Base Clock
1920 MHz
2550 MHz
Boost Clock
2475 MHz
1438 MHz
Memory Clock
1313 MHz
Memory
16GB
Memory Size
12GB
GDDR6X
Memory Type
GDDR6X
256bit
Memory Bus
192bit
736.3GB/s
Bandwidth
504.2GB/s
Render Config
-
-
-
80
SM Count
46
10240
Shading Units
5888
320
TMUs
184
112
ROPs
64
320
Tensor Cores
184
80
RT Cores
46
128 KB (per SM)
L1 Cache
128 KB (per SM)
64 MB
L2 Cache
36 MB
-
-
-
Theoretical Performance
285.6 GPixel/s
Pixel Rate
158.4 GPixel/s
816.0 GTexel/s
Texture Rate
455.4 GTexel/s
52.22 TFLOPS
FP16 (half)
29.15 TFLOPS
52.22 TFLOPS
FP32 (float)
29.15 TFLOPS
816.0 GFLOPS
FP64 (double)
455.4 GFLOPS
Board Design
320W
TDP
200W
700 W
Suggested PSU
550 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 16-pin
Power Connectors
1x 16-pin
Graphics Processor
AD103
GPU Name
AD104
AD103-400-A1
GPU Variant
AD104-250-A1
Ada Lovelace
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
45.9 billion
Transistors
35.8 billion
379 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
1.3
Vulkan
1.3
8.9
CUDA
8.9
6.7
Shader Model
6.7
