Local AI with LM Studio or Ollama
Zush runs local analysis through LM Studio or Ollama on Mac and Windows. You choose and run a compatible model in the local server, then connect Zush to it. Supported analysis stays on your computer while the local mode is selected.
Requirements
Section titled “Requirements”- the latest Zush version for Mac or Windows
- macOS 15 or later, or Windows 10/11
- LM Studio or Ollama installed on the same computer
- a compatible local model with enough disk space and memory for your hardware
- internet access for installation and model download; analysis can run offline afterward
Set up local AI
Section titled “Set up local AI”- Open Zush Settings and select AI Modes.
- Start LM Studio or Ollama and load a compatible model.
- In Zush, select LM Studio or Ollama.
- Confirm the local server address and model.
- Open AI Rename and test a small representative batch.
Choose a local server
Section titled “Choose a local server”| Option | Use it when |
|---|---|
| LM Studio | You want a desktop model catalog and server controls |
| Ollama | You already manage local models through Ollama or prefer its command-line workflow |
Troubleshooting
Section titled “Troubleshooting”| Problem | What to do |
|---|---|
| Zush cannot connect | Confirm that LM Studio or Ollama is running and that the server address matches Zush Settings |
| The model is not listed | Load or pull a compatible model in LM Studio or Ollama, then refresh the model list in Zush |
| Analysis is slow | Try a smaller compatible model or close other memory-intensive apps |
| A file type fails | Test a supported file with a vision-capable model and check the relevant local-server logs |