NVIDIA GeForce RTX 2070 SUPER vs NVIDIA GeForce RTX 5070 Ti
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 2070 SUPER and 16GB VRAM GeForce RTX 5070 Ti to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 2070 SUPER 's Advantages
Lower TDP (215W vs 300W)
NVIDIA GeForce RTX 5070 Ti 's Advantages
Released 5 years and 7 months late
Boost Clock has increased by 39% (2452MHz vs 1770MHz)
More VRAM (16GB vs 8GB)
Larger VRAM bandwidth (896.0GB/s vs 448.0GB/s)
6400 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 2070 SUPER
9.062 TFLOPS
GeForce RTX 5070 Ti
+384%
43.94 TFLOPS
3DMark Time Spy
GeForce RTX 2070 SUPER
10169
GeForce RTX 5070 Ti
+171%
27607
3DMark Time Spy Extreme
GeForce RTX 2070 SUPER
4764
GeForce RTX 5070 Ti
+184%
13531
3DMark Speed Way
GeForce RTX 2070 SUPER
2070
GeForce RTX 5070 Ti
+271%
7699
Graphics Card
Jul 2019
Release Date
Feb 2025
GeForce 20
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1605 MHz
Base Clock
2295 MHz
1770 MHz
Boost Clock
2452 MHz
1750 MHz
Memory Clock
1750 MHz
Memory
8GB
Memory Size
16GB
GDDR6
Memory Type
GDDR7
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
896.0GB/s
Render Config
-
-
-
40
SM Count
70
2560
Shading Units
8960
160
TMUs
280
64
ROPs
96
320
Tensor Cores
280
40
RT Cores
70
64 KB (per SM)
L1 Cache
128 KB (per SM)
4 MB
L2 Cache
48 MB
-
-
-
Theoretical Performance
113.3 GPixel/s
Pixel Rate
235.4 GPixel/s
283.2 GTexel/s
Texture Rate
686.6 GTexel/s
18.12 TFLOPS
FP16 (half)
43.94 TFLOPS
9.062 TFLOPS
FP32 (float)
43.94 TFLOPS
283.2 GFLOPS
FP64 (double)
686.6 GFLOPS
Board Design
215W
TDP
300W
550 W
Suggested PSU
700 W
1x HDMI 2.0
3x DisplayPort 1.4a
1x USB Type-C
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1b
1x 6-pin + 1x 8-pin
Power Connectors
1x 16-pin
Graphics Processor
TU104
GPU Name
GB203
TU104-410-A1
GPU Variant
GB203-300-A1
Turing
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
12 nm
Process Size
5 nm
13.6 billion
Transistors
45.6 billion
545 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
7.5
CUDA
12.0
6.6
Shader Model
6.8
