---
title: "Chat with LLMs Using Open WebUI and Ollama — Troubleshooting"
canonical: "https://build.nvidia.com/playbooks/open-webui/troubleshooting.md"
---

# Common issues with setting up via NVIDIA Sync

| Symptom | Cause | Fix |
|---------|-------|-----|
| Permission denied on docker ps | User not in docker group | Run Docker permissions setup completely, including terminal restart |
| Browser doesn't open automatically | Auto-open setting disabled | Manually navigate to `http://localhost:12000` |
| Model download fails | Network connectivity issues | Check internet connection, retry download |
| GPU not detected in container | Missing `--gpus=all` flag | Recreate the container with the correct start script |
| Port 12000 already in use | Another application using port | Change port in Custom App settings or stop the conflicting service |

# Common issues with manual setup

| Symptom | Cause | Fix |
|---------|-------|-----|
| Permission denied on docker ps | User not in docker group | Run Docker permissions setup completely, including logging out and logging back in, or use sudo |
| Model download fails | Network connectivity issues | Check internet connection, retry download |
| GPU not detected in container | Missing `--gpus=all` flag | Recreate the container with the correct command |
| Port 8080 already in use | Another application using port | Change port in the Docker command or stop the conflicting service |

> [!NOTE]
> Some hardware platforms use Unified Memory Architecture (UMA), which enables dynamic memory sharing between the GPU and CPU. If you hit memory pressure even when within rated capacity, manually flush the buffer cache with:
> ```bash
> sudo sh -c 'sync; echo 3 > /proc/sys/vm/drop_caches'
> ```

For latest known issues, see the documentation linked under **Resources** for your hardware platform.