NVIDIA GeForce RTX 4070 GDDR6 vs NVIDIA GeForce RTX 3060 3840SP
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 GDDR6 and 6GB VRAM GeForce RTX 3060 3840SP to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4070 GDDR6 's Advantages
Released 3 years and 7 months late
Boost Clock has increased by 34% (2475MHz vs 1852MHz)
More VRAM (12GB vs 6GB)
Larger VRAM bandwidth (480.0GB/s vs 336.0GB/s)
2048 additional rendering cores
NVIDIA GeForce RTX 3060 3840SP 's Advantages
Lower TDP (185W vs 200W)
Score
Benchmark
FP32 (float)
GeForce RTX 4070 GDDR6
+104%
29.15 TFLOPS
GeForce RTX 3060 3840SP
14.22 TFLOPS
Graphics Card
Aug 2024
Release Date
Jan 2021
GeForce 40
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1920 MHz
Base Clock
1627 MHz
2475 MHz
Boost Clock
1852 MHz
2500 MHz
Memory Clock
1750 MHz
Memory
12GB
Memory Size
6GB
GDDR6
Memory Type
GDDR6
192bit
Memory Bus
192bit
480.0GB/s
Bandwidth
336.0GB/s
Render Config
-
-
-
46
SM Count
30
5888
Shading Units
3840
184
TMUs
120
64
ROPs
48
184
Tensor Cores
120
46
RT Cores
30
128 KB (per SM)
L1 Cache
128 KB (per SM)
36 MB
L2 Cache
3 MB
-
-
-
Theoretical Performance
158.4 GPixel/s
Pixel Rate
88.90 GPixel/s
455.4 GTexel/s
Texture Rate
222.2 GTexel/s
29.15 TFLOPS
FP16 (half)
14.22 TFLOPS
29.15 TFLOPS
FP32 (float)
14.22 TFLOPS
455.4 GFLOPS
FP64 (double)
222.2 GFLOPS
Board Design
200W
TDP
185W
550 W
Suggested PSU
450 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 16-pin
Power Connectors
1x 12-pin
Graphics Processor
AD104
GPU Name
GA106
AD104-2XX-A1
GPU Variant
GA106-400-A1
Ada Lovelace
Architecture
Ampere
TSMC
Foundry
Samsung
5 nm
Process Size
8 nm
35.8 billion
Transistors
12 billion
294 mm²
Die Size
276 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
8.6
6.8
Shader Model
6.7
