NVIDIA GeForce RTX 3060 vs NVIDIA GeForce RTX 4070
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 3060 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 3060 's Advantages
Lower TDP (170W vs 200W)
NVIDIA GeForce RTX 4070 's Advantages
Released 2 years and 3 months late
Boost Clock has increased by 39% (2475MHz vs 1777MHz)
Larger VRAM bandwidth (504.2GB/s vs 360.0GB/s)
2304 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 3060
12.74 TFLOPS
GeForce RTX 4070
+128%
29.15 TFLOPS
3DMark Time Spy
GeForce RTX 3060
8747
GeForce RTX 4070
+104%
17887
3DMark Time Spy Extreme
GeForce RTX 3060
4097
GeForce RTX 4070
+92%
7907
3DMark Speed Way
GeForce RTX 3060
2181
GeForce RTX 4070
+152%
5508
Shadow of the Tomb Raider 2160p
GeForce RTX 3060
44
GeForce RTX 4070
+86%
82
Shadow of the Tomb Raider 1440p
GeForce RTX 3060
80
GeForce RTX 4070
+100%
160
Shadow of the Tomb Raider 1080p
GeForce RTX 3060
116
GeForce RTX 4070
+120%
256
Cyberpunk 2077 2160p
GeForce RTX 3060
30
GeForce RTX 4070
+80%
54
Cyberpunk 2077 1440p
GeForce RTX 3060
36
GeForce RTX 4070
+158%
93
Cyberpunk 2077 1080p
GeForce RTX 3060
56
GeForce RTX 4070
+132%
130
Battlefield 5 2160p
GeForce RTX 3060
55
GeForce RTX 4070
+78%
98
Battlefield 5 1440p
GeForce RTX 3060
101
GeForce RTX 4070
+70%
172
Battlefield 5 1080p
GeForce RTX 3060
142
GeForce RTX 4070
+40%
200
GTA 5 2160p
GeForce RTX 3060
50
GeForce RTX 4070
+164%
132
GTA 5 1440p
GeForce RTX 3060
82
GeForce RTX 4070
+75%
144
GTA 5 1080p
GeForce RTX 3060
133
GeForce RTX 4070
+42%
190
Horizon Forbidden West 1080p
GeForce RTX 3060
54
GeForce RTX 4070
+87%
101
Horizon Forbidden West 1440p
GeForce RTX 3060
41
GeForce RTX 4070
+90%
78
Horizon Forbidden West 2160p
GeForce RTX 3060
25
GeForce RTX 4070
+96%
49
Graphics Card
Jan 2021
Release Date
Apr 2023
GeForce 30
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1320 MHz
Base Clock
1920 MHz
1777 MHz
Boost Clock
2475 MHz
1875 MHz
Memory Clock
1313 MHz
Memory
12GB
Memory Size
12GB
GDDR6
Memory Type
GDDR6X
192bit
Memory Bus
192bit
360.0GB/s
Bandwidth
504.2GB/s
Render Config
-
-
-
28
SM Count
46
3584
Shading Units
5888
112
TMUs
184
48
ROPs
64
112
Tensor Cores
184
28
RT Cores
46
128 KB (per SM)
L1 Cache
128 KB (per SM)
3 MB
L2 Cache
36 MB
-
-
-
Theoretical Performance
85.30 GPixel/s
Pixel Rate
158.4 GPixel/s
199.0 GTexel/s
Texture Rate
455.4 GTexel/s
12.74 TFLOPS
FP16 (half)
29.15 TFLOPS
12.74 TFLOPS
FP32 (float)
29.15 TFLOPS
199.0 GFLOPS
FP64 (double)
455.4 GFLOPS
Board Design
170W
TDP
200W
450 W
Suggested PSU
550 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 12-pin
Power Connectors
1x 16-pin
Graphics Processor
GA106
GPU Name
AD104
GA106-300-A1
GPU Variant
AD104-250-A1
Ampere
Architecture
Ada Lovelace
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
12 billion
Transistors
35.8 billion
276 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
8.6
CUDA
8.9
6.6
Shader Model
6.7
