NVIDIA GeForce RTX 4070 vs NVIDIA GeForce RTX 2070
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 and 8GB VRAM GeForce RTX 2070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4070 's Advantages
Released 4 years and 6 months late
Boost Clock has increased by 53% (2475MHz vs 1620MHz)
More VRAM (12GB vs 8GB)
Larger VRAM bandwidth (504.2GB/s vs 448.0GB/s)
3584 additional rendering cores
NVIDIA GeForce RTX 2070 's Advantages
Lower TDP (175W vs 200W)
Score
Benchmark
FP32 (float)
GeForce RTX 4070
+290%
29.15 TFLOPS
GeForce RTX 2070
7.465 TFLOPS
3DMark Time Spy
GeForce RTX 4070
+96%
17887
GeForce RTX 2070
9088
3DMark Time Spy Extreme
GeForce RTX 4070
+83%
7907
GeForce RTX 2070
4309
3DMark Speed Way
GeForce RTX 4070
+190%
5508
GeForce RTX 2070
1896
Shadow of the Tomb Raider 2160p
GeForce RTX 4070
+121%
82
GeForce RTX 2070
37
Shadow of the Tomb Raider 1440p
GeForce RTX 4070
+135%
160
GeForce RTX 2070
68
Shadow of the Tomb Raider 1080p
GeForce RTX 4070
+161%
256
GeForce RTX 2070
98
Cyberpunk 2077 2160p
GeForce RTX 4070
+68%
54
GeForce RTX 2070
32
Cyberpunk 2077 1440p
GeForce RTX 4070
+151%
93
GeForce RTX 2070
37
Cyberpunk 2077 1080p
GeForce RTX 4070
+136%
130
GeForce RTX 2070
55
Battlefield 5 2160p
GeForce RTX 4070
+81%
98
GeForce RTX 2070
54
Battlefield 5 1440p
GeForce RTX 4070
+79%
172
GeForce RTX 2070
96
Battlefield 5 1080p
GeForce RTX 4070
+56%
200
GeForce RTX 2070
128
GTA 5 2160p
GeForce RTX 4070
+53%
132
GeForce RTX 2070
86
GTA 5 1440p
GeForce RTX 4070
+60%
144
GeForce RTX 2070
90
GTA 5 1080p
GeForce RTX 4070
+6%
190
GeForce RTX 2070
178
Graphics Card
Apr 2023
Release Date
Oct 2018
GeForce 40
Generation
GeForce 20
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1920 MHz
Base Clock
1410 MHz
2475 MHz
Boost Clock
1620 MHz
1313 MHz
Memory Clock
1750 MHz
Memory
12GB
Memory Size
8GB
GDDR6X
Memory Type
GDDR6
192bit
Memory Bus
256bit
504.2GB/s
Bandwidth
448.0GB/s
Render Config
-
-
-
46
SM Count
36
5888
Shading Units
2304
184
TMUs
144
64
ROPs
64
184
Tensor Cores
288
46
RT Cores
36
128 KB (per SM)
L1 Cache
64 KB (per SM)
36 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
158.4 GPixel/s
Pixel Rate
103.7 GPixel/s
455.4 GTexel/s
Texture Rate
233.3 GTexel/s
29.15 TFLOPS
FP16 (half)
14.93 TFLOPS
29.15 TFLOPS
FP32 (float)
7.465 TFLOPS
455.4 GFLOPS
FP64 (double)
233.3 GFLOPS
Board Design
200W
TDP
175W
550 W
Suggested PSU
450 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 2.0
2x DisplayPort 1.4a
1x USB Type-C
1x 16-pin
Power Connectors
1x 8-pin
Graphics Processor
AD104
GPU Name
TU106
AD104-250-A1
GPU Variant
TU106-400A-A1
Ada Lovelace
Architecture
Turing
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
35.8 billion
Transistors
10.8 billion
295 mm²
Die Size
445 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
7.5
6.7
Shader Model
6.6
