NVIDIA TU116 Graphics Processing Unit (GPU)

Overview
Manufacturer
NVIDIA
Series
GeForce 16
Release Date
February 22nd, 2019
Board Model
NVIDIA PG161
Graphics Processing Unit
GPU Model
TU116-400 (TU116)
Architecture
Turing
Fabrication Process
12 nm FinFET
Die Size
284 mm2
Transistors Count
6.6B
Transistors Density
23.2M TRAN/mm2
CUDAs
1536
TMUs
96
ROPs
48
Clocks
Base Clock
1500 MHz
Boost Clock
1770 MHz
Memory Clock
1500 MHz
Effective Memory Clock
12000 Mbps
Memory Configuration
Memory Size
6144 MB
Memory Type
GDDR6
Memory Bus Width
192-bit
Memory Bandwidth
288.0 GB/s
Physical
Interface
PCI-Express 3.0 x16
Power Connectors
1 × 8-pin
Thermal Design Power
120 W
Recommended PSU
450 W
Display Outputs
DVI-I DualLink
1 ×
DisplayPort
1 ×
HDMI 2.0
1 ×
API Support
DirectX
12.0
Mantle
-
Vulkan
1.0
OpenGL
4.5
OpenCL
2.1
Shader Model
5.0

Performance
Pixel Fillrate
72 GPixels/s
Texture Fillrate
144 GTexel/s
SPFP Performance
5.4 TFLOPS
Performance per W
45.3 GFLOPS/W
Performance per mm2
19.1 GFLOPS/mm2


 ModelGPUClocksMemory
NVIDIA GeForce GTX 1660 Ti TU116-400 1500 / 1500 MHz 6 GB GDDR6
NVIDIA GeForce GTX 1660 TI (Mobile) N18E-G0 1455 / 1500 MHz 6 GB GDDR6
NVIDIA GeForce GTX 1660 TI Max-Q (Mobile) TU116 1140 / 1500 MHz 6 GB GDDR6
NVIDIA GeForce GTX 1660 TU116-300 1530 / 2000 MHz 6 GB GDDR5
NVIDIA GeForce GTX 1660 SUPER TU116-300 1530 / 1750 MHz 6 GB GDDR6
NVIDIA GeForce GTX 1650 SUPER TU116-250 1530 / 1500 MHz 4 GB GDDR6