I do something similar with the base model m4 Mac mini. It's my inference box right now, it handles Immich ML, photo prism AI, and runs Ollama talking to a small web app I call to summarize things. It's summaries are shit. The bigger the model, the more it hallucinates. So I settle for 1B and 4th grade responses
- Posts
- 5
- Comments
- 85
- Joined
- 3 yr. ago
- Posts
- 5
- Comments
- 85
- Joined
- 3 yr. ago
- JumpDeleted
Permanently Deleted
- JumpDeleted
Permanently Deleted
- JumpDeleted
Permanently Deleted
- JumpDeleted
Permanently Deleted
- JumpDeleted
Permanently Deleted
My SO outputs static HTML, moves it to a folder in Nextcloud, and a process syncs it to the server. I don't version her content, just the app code, but the sync target is backed up. I use nginx to serve the HTML at /whatever-folder/some-file-name and inject other client content.