> For the complete documentation index, see [llms.txt](https://docs.quantaria.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.quantaria.xyz/guides/getting-started.md).

# Getting Started

This guide takes you from the Quantaria Console to your first generated text and image with Hilbert-1.

## 1. Sign in

Go to [console.quantaria.xyz](https://console.quantaria.xyz) and sign in.

> **TODO (Quantaria team):** document how to create an account and which sign-in methods are supported.

## 2. Pick a model

Choose between the two live Hilbert-1 models.

|              | Hilbert-1 Nano         | Hilbert-1 Base                                     |
| ------------ | ---------------------- | -------------------------------------------------- |
| Parameters   | \~100M                 | \~1B                                               |
| Text context | 2K tokens              | 8K tokens                                          |
| Image output | 32×32                  | 256×256                                            |
| Architecture | MPS/MPO tensor network | MPS/MPO tensor network with MPO mixture-of-experts |

Use Nano for quick, small-scale experiments. Use Base when you need longer context or larger images.

## 3. Generate text

Enter a prompt and submit it. Keep the prompt plus the expected output within the model's context: 2K tokens for Nano, 8K tokens for Base.

## 4. Generate an image

Request an image and describe what you want. Nano outputs 32×32 images and Base outputs 256×256 images. Expect small, low-resolution outputs from Nano, which is a research-scale model trained on CIFAR-scale images.

## 5. Compare the two models

Run the same prompt on both models to see the difference in text coherence and image detail that the extra scale brings.

## What to expect

* These are research-stage models. Nano and Base are small compared with the largest commercial models.
* Output quality is evaluated against dense transformers of the same size, and results are published either way.
* The models run on GPUs. They do not run on quantum computers.

## Troubleshooting and support

> **TODO (Quantaria team):** add common issues (sign-in problems, generation errors, limits) as they are identified.

For help, email <hello@quantaria.xyz>.

## Next steps

* [Models](https://github.com/bhavy2908/dataai_docs/tree/main/overview/models.md)
* [How It Works](https://github.com/bhavy2908/dataai_docs/tree/main/product/how-it-works.md)
* [Integration Guide](/guides/integration-guide.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.quantaria.xyz/guides/getting-started.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.