# H264 1080p transcoding: RTX 5000 or Tesla T4

**URL:** <https://forums.developer.nvidia.com/t/h264-1080p-transcoding-rtx-5000-or-tesla-t4/129169>\
**Category:** Video Codec, PyNv & OFA\
**Created:** [June 23, 2020, 12:51am UTC](https://forums.developer.nvidia.com/t/h264-1080p-transcoding-rtx-5000-or-tesla-t4/129169 "2020-06-23T00:51:08Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![bpa13](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@bpa13](https://forums.developer.nvidia.com/u/bpa13)\
**Post date:** [June 23, 2020, 12:51am UTC](https://forums.developer.nvidia.com/t/h264-1080p-transcoding-rtx-5000-or-tesla-t4/129169/1 "2020-06-23T00:51:08Z")

</div>

I’m aware of:

> **[Video Encode and Decode GPU Support Matrix](https://developer.nvidia.com/video-encode-and-decode-gpu-support-matrix-new)**
>
> Find the related video encoding and decoding support for all NVIDIA GPU products.

[https://developer.nvidia.com/nvidia-video-codec-sdk](https://developer.nvidia.com/nvidia-video-codec-sdk)

But it do not help me to choose between RTX 5000 or Tesla T4 in order to have the maximum transcoding capacity on  
one machine, in this price range.  
Input: MPEG2@1080 or h264@1080 Output: h264@1080

Thanks

---

<div class="post-metadata">

**Author:** ![mandar\_godse](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/mandar_godse/32/14043_2.png) [@mandar\_godse](https://forums.developer.nvidia.com/u/mandar_godse)\
**Post date:** [July 1, 2020, 11:46am UTC](https://forums.developer.nvidia.com/t/h264-1080p-transcoding-rtx-5000-or-tesla-t4/129169/2 "2020-07-01T11:46:28Z")

</div>

Hi.  
NVIDIA Tesla and Quadro are different product families with different capabilities, reliability metrics, thermal characteristics, support, clocks, memory etc. etc.

You should consider all of these before making your product decision. Tesla T4 indicative encoding benchmarks are available on our web site. Subject to CPU performance, available memory bandwidth, memory clocks, system bottlenecks and software design, the codec performance should scale roughly in proportion to the clock ratio of the two GPUs.

Thanks.