GeForce RTX 4070 Ti SUPER vs Radeon RX 550
We compared two Desktop platform GPUs: 16GB VRAM GeForce RTX 4070 Ti SUPER and 2GB VRAM Radeon RX 550 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 4070 Ti SUPER Advantages
Released 6 years and 9 months late
Boost Clock has increased by 121% (2610MHz vs 1183MHz)
More VRAM (16GB vs 2GB)
Larger VRAM bandwidth (672.3GB/s vs 112.0GB/s)
7936 additional rendering cores
Radeon RX 550 Advantages
Lower TDP (50W vs 285W)
Score
Benchmark
FP32 (float)
GeForce RTX 4070 Ti SUPER
+3541%
44100
Radeon RX 550
1211
3DMark Time Spy
GeForce RTX 4070 Ti SUPER
+1936%
24314
Radeon RX 550
1194
3DMark Time Spy Extreme
GeForce RTX 4070 Ti SUPER
+2074%
11874
Radeon RX 550
546
Shadow of the Tomb Raider 2160p
GeForce RTX 4070 Ti SUPER
+1833%
116
Radeon RX 550
6
Shadow of the Tomb Raider 1440p
GeForce RTX 4070 Ti SUPER
+1733%
220
Radeon RX 550
12
Shadow of the Tomb Raider 1080p
GeForce RTX 4070 Ti SUPER
+1319%
298
Radeon RX 550
21
Battlefield 5 2160p
GeForce RTX 4070 Ti SUPER
+1785%
132
Radeon RX 550
7
Battlefield 5 1440p
GeForce RTX 4070 Ti SUPER
+1328%
200
Radeon RX 550
14
Battlefield 5 1080p
GeForce RTX 4070 Ti SUPER
+900%
200
Radeon RX 550
20
GTA 5 1080p
GeForce RTX 4070 Ti SUPER
+126%
190
Radeon RX 550
84
Graphics Card
Jan 2024
Release Date
Apr 2017
GeForce 40
Generation
Polaris
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x8
Clock Speeds
2340 MHz
Base Clock
1100 MHz
2610 MHz
Boost Clock
1183 MHz
1313 MHz
Memory Clock
1750 MHz
Memory
16GB
Memory Size
2GB
GDDR6X
Memory Type
GDDR5
256bit
Memory Bus
128bit
672.3GB/s
Bandwidth
112.0GB/s
Render Config
-
Compute Units
8
66
SM Count
-
8448
Shading Units
512
264
TMUs
32
96
ROPs
16
264
Tensor Cores
-
66
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
48 MB
L2 Cache
512 KB
Theoretical Performance
250.6 GPixel/s
Pixel Rate
18.93 GPixel/s
689.0 GTexel/s
Texture Rate
37.86 GTexel/s
44.10 TFLOPS
FP16 (half)
1211 GFLOPS
44.10 TFLOPS
FP32 (float)
1211 GFLOPS
689.0 GFLOPS
FP64 (double)
75.71 GFLOPS
Board Design
285W
TDP
50W
600 W
Suggested PSU
250 W
1x HDMI 2.1
3x DisplayPort 1.4a
3x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 2.0b
1x DisplayPort 1.4a
1x HDMI 2.0b
1x DisplayPort 1.4a
1x 16-pin
Power Connectors
None
Graphics Processor
AD103
GPU Name
Lexa
AD103-275-A1
GPU Variant
Lexa PRO
(215-0904018)
(215-0904018)
Ada Lovelace
Architecture
GCN 4.0
TSMC
Foundry
GlobalFoundries
5 nm
Process Size
14 nm
45.9 billion
Transistors
2.2 billion
379 mm²
Die Size
103 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
8.9
CUDA
-
6.7
Shader Model
6.4