Self-Host Ollama with Docker Compose
Ollama bundles model weights, configuration, and data into a single package. Run, customize, and serve state-of-the-art open-source LLMs through a local REST API.
Minimum Hardware Requirements
version: '3.8'
services:
ollama:
image: ollama/ollama:latest
container_name: ollama
restart: unless-stopped
ports:
- "11434:11434"
environment:
- NODE_ENV=production
- TZ=UTC
volumes:
- ollama_data:/data
volumes:
ollama_data:
driver: localdocker-compose.yml and run:
docker compose up -d
VPS RAM & Server Sizing Calculator
Planning to run Ollama alone or alongside other self-hosted containers on one VPS? Toggle apps to calculate your exact RAM needs with a 25% safety buffer.
Matched Cloud VPS Tiers for Selected Workload:
Replaces OpenAI API
Commercial cloud solution with per-user monthly subscription fees.
More Ai Llms Apps View All →
Compare Ollama
Benchmark specs head-to-head with other open-source alternatives
Compare Ollama Side-by-Side
Select any open-source tool from the dropdown to run a hardware, memory, and popularity benchmark against Ollama.