Skip to main content

​
Overview

Before deploying Smallest Self-Host with Docker, ensure your system meets the hardware and software requirements. This guide walks you through everything you need to prepare your environment.

​
Hardware Requirements

​
Minimum Specifications

CPU

4 cores minimum8+ cores recommended for production

RAM

16 GB minimum32+ GB recommended for production

GPU

NVIDIA GPU required
  • L4 or L40s (recommended)
  • A10, A100, H100, T4 (supported)
  • Minimum 16GB VRAM

Storage

100 GB minimum
  • 50 GB for models
  • 50 GB for logs and data

​
Software Requirements

​
Operating System

Smallest Self-Host supports the following operating systems: 
Ubuntu 20.04 LTS or later
Ubuntu 22.04 LTS (recommended)
Debian 11 or later

​
Required Software

1

Docker

Docker Engine 20.10 or later
docker --version
Expected output: Docker version 20.10.0 or higher
2

Docker Compose

Docker Compose 2.0 or later
docker compose version
Expected output: Docker Compose version v2.0.0 or higher
3

NVIDIA Driver

NVIDIA Driver 525+ for newer GPUs (A10, A100, L4)NVIDIA Driver 470+ for older GPUs (T4, V100)
nvidia-smi
Should display GPU information without errors
4

NVIDIA Container Toolkit

Required for GPU access in containers
nvidia-container-cli --version

​
Installation Guides

​
Install Docker

sudo apt-get update
sudo apt-get install -y ca-certificates curl gnupg

sudo install -m 0755 -d /etc/apt/keyrings
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | \
  sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg
sudo chmod a+r /etc/apt/keyrings/docker.gpg

echo \
  "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] \
  https://download.docker.com/linux/ubuntu \
  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
  sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

sudo apt-get update
sudo apt-get install -y docker-ce docker-ce-cli containerd.io \
  docker-buildx-plugin docker-compose-plugin

sudo usermod -aG docker $USER
newgrp docker

​
Install NVIDIA Driver

sudo apt-get update
sudo apt-get install -y ubuntu-drivers-common

sudo ubuntu-drivers autoinstall

sudo reboot
After reboot, verify:
nvidia-smi

​
Install NVIDIA Container Toolkit

distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/libnvidia-container/gpgkey | \
  sudo apt-key add -
curl -s -L https://nvidia.github.io/libnvidia-container/$distribution/libnvidia-container.list | \
  sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list

sudo apt-get update
sudo apt-get install -y nvidia-container-toolkit

sudo systemctl restart docker

​
Verify GPU Access

Test that Docker can access the GPU: 
docker run --rm --gpus all nvidia/cuda:11.8.0-base-ubuntu22.04 nvidia-smi
You should see your GPU information displayed.

​
Credentials

Before installation, obtain the following from Smallest.ai:
Your unique license key for validationContact: [email protected]
Credentials to pull Docker images:
  • Registry URL: quay.io
  • Username
  • Password
  • Email
Contact: [email protected]
Download URLs for ASR modelsContact: [email protected]

​
Network Requirements

Ensure the following ports are available:
PortServicePurpose
7100API ServerClient API requests
2233Lightning ASRInternal ASR processing
6699License ProxyInternal license validation
6379RedisInternal caching
The License Proxy requires outbound HTTPS access to Smallest’s license servers for validation. Ensure your firewall allows outbound connections to:
  • console-api.smallest.ai (port 443)

​
Verification Checklist

Before proceeding to installation, verify:
1

Docker Running

docker ps
Should execute without errors
2

GPU Accessible

docker run --rm --gpus all nvidia/cuda:11.8.0-base-ubuntu22.04 nvidia-smi
Should display GPU information
3

Credentials Ready

  • License key obtained
  • Container registry username and password
  • Model download URLs
4

Ports Available

sudo netstat -tuln | grep -E '(7100|2233|6699|6379)'
Should return no results (ports free)

​
What’s Next?

Once all prerequisites are met, proceed to the quick start guide:

STT Quick Start

Deploy Smallest Self-Host STT with Docker Compose