homelab-codex-ws/services/ollama/README.md

14 lines
226 B
Markdown
Raw Normal View History

2026-05-11 20:46:50 +02:00
# Ollama
Get up and running with large language models locally.
## Usage
Deployed on the `solaria` node for GPU acceleration.
API is available on port 11434.
Example check:
```bash
curl http://localhost:11434/api/tags
```