# Windows Alpha for AMD & Nvidia GTX GPUs only **URL:** \ **Category:** Video AI Beta\ **Created:** [February 16, 2023, 10:51pm UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259 "2023-02-16T22:51:08Z")\ **Posts on this page:** 10\ **Page:** 1
**Author:** ![suraj](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/s/ecccb3/32.png) [@suraj](https://community.topazlabs.com/u/suraj)\ **Post date:** [February 16, 2023, 10:51pm UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259/1 "2023-02-16T22:51:08Z")
Hi All, Here is an early version of app that should improve performance for AMD GPUs and hopefully older Nvidia GPUs(non RTX cards) that use onnx models. Download: [Win](https://downloads.topazlabs.com/deploy/TopazVideoAIAlpha/3.1.6.0.a%2bamd/TopazVideoAIAlpha-3.1.6.0.a%2bamd.msi) **Known Issues** : - Proteus Auto will not work, use Proteus with manual settings - Models cannot be run on CPU - Models cannot be run on intel GPU - Models run slower on RTX GPUs Thank you for testing PS: Since this is an alpha version, it will not interfere with Beta or Release versions on the machine. ---
**Author:** ![david.123](https://community.topazlabs.com/user_avatar/community.topazlabs.com/david.123/32/163156_2.png) [@david.123](https://community.topazlabs.com/u/david.123)\ **Post date:** [February 17, 2023, 12:47am UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259/2 "2023-02-17T00:47:18Z")
Thanks for this! Is there any optimal value we should be setting the memory usage to? Or just leave it at 100%? Which leads into my thought that it would be ideal if the program calculated and set the memory use sizes optimally on it’s own without user intervention (or even visibility to it). ---
**Author:** ![suraj](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/s/ecccb3/32.png) [@suraj](https://community.topazlabs.com/u/suraj)\ **Post date:** [February 17, 2023, 3:37pm UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259/3 "2023-02-17T15:37:09Z")
100% in most cases should be fine unless running too many filters. Eventually yes, it is lot more complicated due to the GUI allowing multiple simultaneous processes. ---
**Author:** ![TPX](https://community.topazlabs.com/user_avatar/community.topazlabs.com/tpx/32/194727_2.png) [@TPX](https://community.topazlabs.com/u/TPX)\ **Post date:** [February 17, 2023, 4:57pm UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259/4 "2023-02-17T16:57:12Z")
Notice: Lowering Memory to 50% did speed up the process by 70% on my system. So 16 - 17 fps instead of 10. look at your models folder, it should use the 288px models. ---
**Author:** ![Martyprod](https://community.topazlabs.com/user_avatar/community.topazlabs.com/martyprod/32/36109_2.png) [@Martyprod](https://community.topazlabs.com/u/Martyprod)\ **Post date:** [February 19, 2023, 7:13am UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259/5 "2023-02-19T07:13:16Z")
Proteus Manual (No setting moved) tested on 1050ti GTX, 720p → 1080p 59.97 = usual speed, 0.79 seconds per frame. around 0.78 with the last beta. ---
**Author:** ![david.123](https://community.topazlabs.com/user_avatar/community.topazlabs.com/david.123/32/163156_2.png) [@david.123](https://community.topazlabs.com/u/david.123)\ **Post date:** [February 19, 2023, 11:55pm UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259/6 "2023-02-19T23:55:57Z")
I tested this version vs 3.0.15 release and didn’t see any notable difference in performance on GTX 1070, everything was with about 2% of each other between versions. Perhaps it made a bigger difference to AMD GPUs. ---
**Author:** ![TPX](https://community.topazlabs.com/user_avatar/community.topazlabs.com/tpx/32/194727_2.png) [@TPX](https://community.topazlabs.com/u/TPX)\ **Post date:** [February 20, 2023, 1:56pm UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259/7 "2023-02-20T13:56:02Z")
Did you try to lower memory in settings below 50%? ---
**Author:** ![david.123](https://community.topazlabs.com/user_avatar/community.topazlabs.com/david.123/32/163156_2.png) [@david.123](https://community.topazlabs.com/u/david.123)\ **Post date:** [February 20, 2023, 6:36pm UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259/8 "2023-02-20T18:36:01Z")
Yes, and the performance with memory set lower was worse in every scenario I tested: GTX1070 8GB + Intel 6700K + 16 GB RAM + Windows 11 Alpha v3.1.6.0.a+amd 720p source, 2x upscale to 1440p, max mem 45%: Artemis HQ: 0.31spf Gaia HQ: 0.88spf Proteus: 0.31spf 720p source, 2x upscale to 1440p, max mem 100%: Artemis HQ: 0.29spf Gaia HQ: 0.82spf Proteus: 0.29spf 1080p source, no upscale, max mem 45%: Artemis HQ: 0.53spf Gaia HQ: 1.39spf Proteus: 0.53spf 1080p source, no upscale, max mem 100%: Artemis HQ: 0.45spf Gaia HQ: 1.19spf Proteus: 0.46spf Chronos Fast: 720p source, Chronos Fast 2x frame double: 0.17spf max mem 45% 720p source, Chronos Fast 2x frame double: 0.15spf max mem 100% 1080p source, Chronos Fast 2x frame double: 0.57spf max mem 45% 1080p source, Chronos Fast 2x frame double: 0.44spf max mem 100% ---
**Author:** ![suraj](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/s/ecccb3/32.png) [@suraj](https://community.topazlabs.com/u/suraj)\ **Post date:** [February 22, 2023, 8:50pm UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259/9 "2023-02-22T20:50:27Z")
There is an updated version posted here > [@Windows Alpha 2 for AMD & Nvidia GTX GPUs only](https://community.topazlabs.com/t/windows-alpha-2-for-amd-nvidia-gtx-gpus-only/40587): > > Hi All, Here is a version of the app with all onnx specific optimizations complete. This version should be almost 2X faster and should work for all Nvidia(non RTX) and AMD GPUs. Please let us know if there is no speed up or drop in performance. Download: [Win](https://downloads.topazlabs.com/deploy/TopazVideoAIAlpha/3.1.7.1.amd/TopazVideoAIAlpha-3.1.7.1.amd.msi) Known Issues: Proteus Auto will not work, use Proteus with manual settings Models cannot be run on CPU Models cannot be run on intel GPU Models run slower on RTX GPUs Thank you for testing, let us know if you have any issues. PS: Sinc… ---
**Author:** ![suraj](https://community.topazlabs.com/letter_avatar_proxy/v4/letter/s/ecccb3/32.png) [@suraj](https://community.topazlabs.com/u/suraj)\ **Post date:** [February 22, 2023, 8:50pm UTC](https://community.topazlabs.com/t/windows-alpha-for-amd-nvidia-gtx-gpus-only/40259/10 "2023-02-22T20:50:39Z")