NVIDIA GeForce GTX 1660 Ti vs NVIDIA GeForce RTX 3070 Ti GA102
We compared two Desktop platform GPUs: 6GB VRAM GeForce GTX 1660 Ti and 8GB VRAM GeForce RTX 3070 Ti GA102 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce GTX 1660 Ti 's Advantages
Lower TDP (120W vs 290W)
NVIDIA GeForce RTX 3070 Ti GA102 's Advantages
Released 3 years and 8 months late
More VRAM (8GB vs 6GB)
Larger VRAM bandwidth (608.3GB/s vs 288.0GB/s)
4608 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce GTX 1660 Ti
5.437 TFLOPS
GeForce RTX 3070 Ti GA102
+300%
21.75 TFLOPS
3DMark Time Spy
GeForce GTX 1660 Ti
6346
GeForce RTX 3070 Ti GA102
+134%
14872
3DMark Time Spy Extreme
GeForce GTX 1660 Ti
2883
GeForce RTX 3070 Ti GA102
+157%
7416
Graphics Card
Feb 2019
Release Date
Oct 2022
GeForce 16
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1500 MHz
Base Clock
1575 MHz
1770 MHz
Boost Clock
1770 MHz
1500 MHz
Memory Clock
1188 MHz
Memory
6GB
Memory Size
8GB
GDDR6
Memory Type
GDDR6X
192bit
Memory Bus
256bit
288.0GB/s
Bandwidth
608.3GB/s
Render Config
-
-
-
24
SM Count
48
1536
Shading Units
6144
96
TMUs
192
48
ROPs
96
-
Tensor Cores
192
-
RT Cores
48
64 KB (per SM)
L1 Cache
128 KB (per SM)
1536 KB
L2 Cache
4 MB
-
-
-
Theoretical Performance
84.96 GPixel/s
Pixel Rate
169.9 GPixel/s
169.9 GTexel/s
Texture Rate
339.8 GTexel/s
10.87 TFLOPS
FP16 (half)
21.75 TFLOPS
5.437 TFLOPS
FP32 (float)
21.75 TFLOPS
169.9 GFLOPS
FP64 (double)
339.8 GFLOPS
Board Design
120W
TDP
290W
300 W
Suggested PSU
600 W
1x DVI
1x HDMI 2.0
1x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 12-pin
Graphics Processor
TU116
GPU Name
GA102
TU116-400-A1
GPU Variant
GA102-150-A1
Turing
Architecture
Ampere
TSMC
Foundry
Samsung
12 nm
Process Size
8 nm
6.6 billion
Transistors
28.3 billion
284 mm²
Die Size
628 mm²
Graphics Features
12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
7.5
CUDA
8.6
6.6
Shader Model
6.6
