GeForce GTX 1660 Ti and Radeon HD 3850 - video card comparison
Passmark - benchmark score GeForce GTX 1660 Ti vs Radeon HD 3850
GeForce GTX 1660 Ti
13314
Radeon HD 3850
404
GeForce GTX 1660 Ti
Radeon HD 3850
Architecture
Turing (2018−2021)
TeraScale (2005−2013)
GPU code name
Turing TU116
RV670
Market segment
Desktop
Desktop
Release date
February 2019
November 2007
Interface
PCIe 3.0 x16
PCIe 2.0 x16
Supplementary power connectors
1x 8-pin
1x 6-pin
Boost clock speed
1770 MHz
-
Core clock speed
1500 MHz
668 MHz
Floating-point performance
-
427.5 gflops
Manufacturing process technology
12 nm
55 nm
Number of transistors
6,600 million
666 million
Pipelines / CUDA cores
1536
320
Power consumption (TDP)
120 Watt
75 Watt
Texture fill rate
169.9
10.69
Memory type
GDDR6
GDDR3
Maximum RAM amount
6 GB
1 GB
Memory bus width
192 Bit
256 Bit
Memory clock speed
12000 MHz
1660 MHz
Memory bandwidth
288.0 GB/s
53.12 GB/s
Shared memory
-
-
Display Connectors
1x DVI, 1x HDMI, 1x DisplayPort
2x DVI, 1x S-Video
HDMI
+
-
DirectX
12 (12_1)
10.1 (10_1)
CUDA
7.5
-
OpenCL
1.2
N/A
OpenGL
4.6
3.3
Shader Model
6.5
4.1
Vulkan
1.2.131
N/A