Below the models directory you will find a structure similar to the following:
```shell
.
├── blobs
└── manifests
└── registry.ollama.ai
├── f0rodo
├── library
├── mattw
└── saikatkumardey
```
There is a `manifests/registry.ollama.ai/namespace` path. In example above, the user has downloaded models from the official `library`, `f0rodo`, `mattw`, and `saikatkumardey` namespaces. Within each of those directories, you will find directories for each of the models downloaded. And in there you will find a file name representing each tag. Each tag file is the manifest for the model.
The manifest lists all the layers used in this model. You will see a `media type` for each layer, along with a digest. That digest corresponds with a file in the `models/blobs directory`.
To modify where models are stored, you can use the `OLLAMA_MODELS` environment variable. Note that on Linux this means defining `OLLAMA_MODELS` in a drop-in `/etc/systemd/system/ollama.service.d` service file, reloading systemd, and restarting the ollama service.
## Does Ollama send my prompts and answers back to Ollama.ai to use in any way?
No. Anything you do with Ollama, such as generate a response from the model, stays with you. We don't collect any data about how you use the model. You are always in control of your own data.
There is already a large collection of plugins available for VSCode as well as other editors that leverage Ollama. You can see the list of [extensions & plugins](https://github.com/jmorganca/ollama#extensions--plugins) at the bottom of the main repository readme.
Ollama is compatible with proxy servers if `HTTP_PROXY` or `HTTPS_PROXY` are configured. When using either variables, ensure it is set where `ollama serve` can access the values.
When using `HTTPS_PROXY`, ensure the proxy certificate is installed as a system certificate.
Alternatively, Docker daemon can be configured to use a proxy. Instructions are available for Docker Desktop on [macOS](https://docs.docker.com/desktop/settings/mac/#proxies), [Windows](https://docs.docker.com/desktop/settings/windows/#proxies), and [Linux](https://docs.docker.com/desktop/settings/linux/#proxies), and Docker [daemon with systemd](https://docs.docker.com/config/daemon/systemd/#httphttps-proxy).
Ensure the certificate is installed as a system certificate when using HTTPS. This may require a new Docker image when using a self-signed certificate.
The Ollama Docker container can be configured with GPU acceleration in Linux or Windows (with WSL2). This requires the [nvidia-container-toolkit](https://github.com/NVIDIA/nvidia-container-toolkit). See [ollama/ollama](https://hub.docker.com/r/ollama/ollama) for more details.