AMD Radeon RX 7900 XT vs NVIDIA GeForce RTX 4070 SUPER
We compared two Desktop platform GPUs: 20GB VRAM Radeon RX 7900 XT and 12GB VRAM GeForce RTX 4070 SUPER to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon RX 7900 XT 's Advantages
More VRAM (20GB vs 12GB)
Larger VRAM bandwidth (800.0GB/s vs 504.2GB/s)
NVIDIA GeForce RTX 4070 SUPER 's Advantages
Released 1 years and 2 months late
Boost Clock has increased by 3% (2475MHz vs 2394MHz)
1792 additional rendering cores
Lower TDP (220W vs 300W)
Score
Benchmark
FP32 (float)
Radeon RX 7900 XT
+45%
51.48 TFLOPS
GeForce RTX 4070 SUPER
35.48 TFLOPS
3DMark Time Spy
Radeon RX 7900 XT
+27%
26829
GeForce RTX 4070 SUPER
21035
3DMark Time Spy Extreme
Radeon RX 7900 XT
+31%
13130
GeForce RTX 4070 SUPER
9967
3DMark Speed Way
Radeon RX 7900 XT
+2%
5364
GeForce RTX 4070 SUPER
5241
Blender
Radeon RX 7900 XT
3905
GeForce RTX 4070 SUPER
+75%
6872
Shadow of the Tomb Raider 2160p
Radeon RX 7900 XT
+8%
102
GeForce RTX 4070 SUPER
94
Shadow of the Tomb Raider 1440p
Radeon RX 7900 XT
+11%
205
GeForce RTX 4070 SUPER
184
Shadow of the Tomb Raider 1080p
Radeon RX 7900 XT
+8%
299
GeForce RTX 4070 SUPER
276
Cyberpunk 2077 2160p
Radeon RX 7900 XT
50
GeForce RTX 4070 SUPER
+22%
61
Cyberpunk 2077 1440p
Radeon RX 7900 XT
94
GeForce RTX 4070 SUPER
+14%
108
Cyberpunk 2077 1080p
Radeon RX 7900 XT
+5%
158
GeForce RTX 4070 SUPER
150
GTA 5 2160p
Radeon RX 7900 XT
+18%
170
GeForce RTX 4070 SUPER
144
GTA 5 1440p
Radeon RX 7900 XT
+7%
170
GeForce RTX 4070 SUPER
158
GTA 5 1080p
Radeon RX 7900 XT
190
GeForce RTX 4070 SUPER
190
Horizon Forbidden West 1080p
Radeon RX 7900 XT
+16%
131
GeForce RTX 4070 SUPER
112
Horizon Forbidden West 1440p
Radeon RX 7900 XT
+22%
105
GeForce RTX 4070 SUPER
86
Horizon Forbidden West 2160p
Radeon RX 7900 XT
+25%
68
GeForce RTX 4070 SUPER
54
Graphics Card
Nov 2022
Release Date
Jan 2024
Navi III
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1387 MHz
Base Clock
1980 MHz
2394 MHz
Boost Clock
2475 MHz
2500 MHz
Memory Clock
1313 MHz
Memory
20GB
Memory Size
12GB
GDDR6
Memory Type
GDDR6X
320bit
Memory Bus
192bit
800.0GB/s
Bandwidth
504.2GB/s
Render Config
84
Compute Units
-
-
SM Count
56
5376
Shading Units
7168
336
TMUs
224
192
ROPs
80
-
Tensor Cores
224
84
RT Cores
56
256 KB per Array
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
48 MB
80 MB
L3 Cache
-
Theoretical Performance
459.6 GPixel/s
Pixel Rate
198.0 GPixel/s
804.4 GTexel/s
Texture Rate
554.4 GTexel/s
103.0 TFLOPS
FP16 (half)
35.48 TFLOPS
51.48 TFLOPS
FP32 (float)
35.48 TFLOPS
1.609 TFLOPS
FP64 (double)
554.4 GFLOPS
Board Design
300W
TDP
220W
700 W
Suggested PSU
550 W
1x HDMI 2.1a
2x DisplayPort 2.1
1x USB Type-C
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
2x 8-pin
Power Connectors
1x 16-pin
Graphics Processor
Navi 31
GPU Name
AD104
Navi 31 XT
(215-145000156)
GPU Variant
AD104-350-A1
RDNA 3.0
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
57.7 billion
Transistors
35.8 billion
529 mm²
Die Size
294 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.2
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
8.9
6.7
Shader Model
6.8
