Gigabyte GeForce GTX 1660 Gaming OC review - The GPU Specifications

Turing TU116 GPU Specifications

The GPU TU116 for the GeForce GTX 1660 and 1660 Ti contains 6.6 billion transistors localized on the die. In comparison, Pascal had close to 12 billion transistors on a die size of 471mm2. Gamers will immediately look at the shader processors; the Quadro RTX 8000 has 4608 of them enabled and since everything with bits is in multitudes of eight and while looking at the GPU die photos; it has 24 SMs (streaming multiprocessors) each holding 64 cores = 1536 Shader processors. This GPU is fabbed on an optimized 12nm TSMC FinFET+ node and the full GPU is unlocked. Since the GeForce GTX 1660 is using the same chip as the Ti and has 1408 Shader processors we can quickly conclude that 1408/64 the unit has 22 shader clusters. Each shader cluster has four Texture units, so that makes up for 88 of them. 

Next, to a slightly reconfigured shader count, the secondary change for the GTX 1660 is its memory. NVIDIA fits this card series with cheaper GDDR5 memory, which will offer less bandwidth, 192 Gb/sec over 288 GB/s for the Ti model. That difference is substantial and will make the card perform quite a bit slower than the Ti version. Of course, you can always try to tweak the memory bandwidth, which we'll show you in our tweaking segment of this article.