# What does VEAI performance look like between AMD/NVIDIA? **URL:** \ **Category:** General\ **Created:** [December 15, 2020, 9:22am UTC](https://community.topazlabs.com/t/what-does-veai-performance-look-like-between-amd-nvidia/18581 "2020-12-15T09:22:52Z")\ **Posts on this page:** 1\ **Showing post:** 42
**Author:** ![lhkjacky](https://community.topazlabs.com/user_avatar/community.topazlabs.com/lhkjacky/32/256798_2.png) [@lhkjacky](https://community.topazlabs.com/u/lhkjacky)\ **Post date:** [January 31, 2021, 12:18pm UTC](https://community.topazlabs.com/t/what-does-veai-performance-look-like-between-amd-nvidia/18581/42 "2021-01-31T12:18:20Z")
> [@57110621](#): > > The hardware coding of different brands of graphics cards will also affect the production speed. It seems that NVIDIA’s software support and development is better than AMD. > [@57110621](#): > > There is a big gap between AMD and NVIDIA graphics hardware encoding speeds, such as ffmpeg H.264 used by VEAI. This is why we can’t just look at hardware devices and ignore software development and compatibility. And this is AMD’s weakness. VEAI use CPU to decode and encode not GPU. “NVIDIA NVENC” is better than “AMD VCE”, but it is irrelevant here, because VEAI is not using hardware encoder. Just like pointing out RTX3000 series is better than AMD RX6000 series for Ray-tracing game benchmark is meaningless, because VEAI won’t get any benefit from those extra Ray-Tracing cores. For more detail, you may refer to the post from developer. > [@VEAI Performance](https://community.topazlabs.com/t/veai-performance/19177/1): > > All decoding/encoding is done on the CPU, so an older CPU will lead to slower performance unless using older codecs or uncompressed image formats like TIF. --- _[View the full topic](https://community.topazlabs.com/t/what-does-veai-performance-look-like-between-amd-nvidia/18581)._