NVIDIA GeForce RTX 3060 Ti GDDR6X vs NVIDIA GeForce RTX 4070 AD103
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3060 Ti GDDR6X and 12GB VRAM GeForce RTX 4070 AD103 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 3060 Ti GDDR6X 's Advantages
Larger VRAM bandwidth (608.3GB/s vs 504.2GB/s)
NVIDIA GeForce RTX 4070 AD103 's Advantages
Released 1 years and 5 months late
Boost Clock has increased by 49% (2475MHz vs 1665MHz)
More VRAM (12GB vs 8GB)
1024 additional rendering cores
Lower TDP (200W vs 225W)
Score
Benchmark
FP32 (float)
GeForce RTX 3060 Ti GDDR6X
16.2 TFLOPS
GeForce RTX 4070 AD103
+79%
29.15 TFLOPS
Graphics Card
Oct 2022
Release Date
Mar 2024
GeForce 30
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1410 MHz
Base Clock
1920 MHz
1665 MHz
Boost Clock
2475 MHz
1188 MHz
Memory Clock
1313 MHz
Memory
8GB
Memory Size
12GB
GDDR6X
Memory Type
GDDR6X
256bit
Memory Bus
192bit
608.3GB/s
Bandwidth
504.2GB/s
Render Config
-
-
-
38
SM Count
46
4864
Shading Units
5888
152
TMUs
184
80
ROPs
64
152
Tensor Cores
184
38
RT Cores
46
128 KB (per SM)
L1 Cache
128 KB (per SM)
4 MB
L2 Cache
36 MB
-
-
-
Theoretical Performance
133.2 GPixel/s
Pixel Rate
158.4 GPixel/s
253.1 GTexel/s
Texture Rate
455.4 GTexel/s
16.20 TFLOPS
FP16 (half)
29.15 TFLOPS
16.20 TFLOPS
FP32 (float)
29.15 TFLOPS
253.1 GFLOPS
FP64 (double)
455.4 GFLOPS
Board Design
225W
TDP
200W
550 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
GA104
GPU Name
AD103
GA104-202-A1
GPU Variant
AD103-175-K1-A1
Ampere
Architecture
Ada Lovelace
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
17.4 billion
Transistors
45.9 billion
392 mm²
Die Size
379 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
6.7
Shader Model
6.7
