Official · AI/ML · 1 docker
ollama
Ollama
Run open-source LLMs locally with a simple API.
preflight
topology
How this stack is wired
Each card is a service this deploy creates. A line means one service reads another through env.
binds
Paths this deploy mounts
Host path on the node, then the path inside the container.
ollama
/var/lib/dokku/data/storage/ollama/default
/root/.ollama
listen
Ports the stack publishes
Service on the left. Host port, then the container port and scheme.
- ollama80→11434/http
you set
Values this template leaves for you
Literals and placeholders. Wiring to another service lives on the topology, not here.
OLLAMA_HOST
ollama
0.0.0.0:11434
OLLAMA_ORIGINS
ollama
*
notes
Context for this stack
Written with the template. Topology, binds, and values you set live in the sections above.
Ollama is an open-source platform for running large language models locally. It makes it easy to download, manage, and serve models like Llama, Mistral, Gemma, Qwen, DeepSeek, and many others through a simple API.
About Hosting Ollama
This dFlow template deploys Ollama using the official Docker image, providing a self-hosted API for running AI models on your own infrastructure. Connect your applications, AI agents, or tools to Ollama and manage models with full control over your environment.
Common Use Cases
- Run open-source LLMs locally
- Power AI applications and chatbots
- Serve models for Open WebUI, Langflow, and AI agents
- Build private AI APIs without relying on cloud providers
- Experiment with multiple language models
Dependencies
- Ollama (Official Docker image)
Why Deploy on dFlow?
Deploy Ollama in minutes with automatic HTTPS, persistent storage, environment variable management, custom domains, and centralized application management—all from a single dashboard.