# Requirements

## Hardware requirements

* CPU recommended: 3-4 threads as the base and 1-2 cores per worker on each machine.
* GPU Nvidia (consumer and professional) [computer capability](https://developer.nvidia.com/cuda-gpus) >= sm\_37 for optimal performance
* RAM GPU 4-6 GB for 1 worker depending of the resolution
* RAM > 16 GB
* 60 Go + local storage

## Software dependencies

* Linux Ubuntu >= 20.04 / CentOS >= 8 / Amazon Linux 2 Deep Learning AMI GPU 
* Windows 10 Pro, 11 Pro and server 2022 with Windows Subsystem for Linux (WSL)
* Install the following dependencies either using the provided script ([Linux](https://doc-op.blurit.io/2.0/blurit-on-premise/installation/linux-dependencies) only) or manually ([Linux](https://doc-op.blurit.io/2.0/blurit-on-premise/installation/linux-dependencies) or [Windows](https://doc-op.blurit.io/2.0/blurit-on-premise/installation/windows-dependencies-wsl)):
  * [nvidia drivers](https://www.nvidia.com/download/index.aspx) recommended >= 470
  * [docker ce](https://docs.docker.com/engine/install/) and [post install linux](https://.docker.com/engine/install/linux-postinstall/)
  * [docker desktop](https://docs.docker.com/desktop/install/windows-install/) for Windows WSL
  * docker-compose <= 1.29
  * [nvidia-docker2](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html#setting-up-nvidia-container-toolkit) (set as default docker runtime)

## Blurit archive

* blurit\_stack.yml
* .env
* Blurit-op.postman\_collection.json
* README.md
* licence.txt
* login-registry.txt
* install\_dependencies.sh

###