> 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/quantaria-console.md).

# Quantaria Console

The Quantaria Console at [console.quantaria.xyz](https://console.quantaria.xyz) is where you use Quantaria models. Hilbert-1 Nano and Hilbert-1 Base are live there today.

|              | Hilbert-1 Nano | Hilbert-1 Base |
| ------------ | -------------- | -------------- |
| Parameters   | \~100M         | \~1B           |
| Text context | 2K tokens      | 8K tokens      |
| Image output | 32×32          | 256×256        |

Both models generate text and images from one tensor-network backbone.

## What you can do

* Sign in to the console.
* Choose Hilbert-1 Nano or Hilbert-1 Base.
* Generate text and generate images.

See [Getting Started](https://github.com/bhavy2908/dataai_docs/tree/main/guides/getting-started.md) for a walkthrough.

## Choosing a model

| If you want to                      | Use            | Why                                                              |
| ----------------------------------- | -------------- | ---------------------------------------------------------------- |
| Try the models for the first time   | Hilbert-1 Nano | Smaller and faster to try, with a 2K-token context               |
| Work with long prompts or documents | Hilbert-1 Base | 8K-token context, so more fits in one request                    |
| Look at larger images               | Hilbert-1 Base | 256×256 output, against 32×32 for Nano                           |
| Compare quality                     | Both           | Run the same prompt on each and compare the outputs side by side |

Nano and Base are research-scale models, so expect small and imperfect outputs, especially from Nano. The published benchmarks will show how each model compares with a dense transformer of the same size.

## Limits to keep in mind

* Keep your prompt and the expected output inside the model's context: 2K tokens for Nano and 8K for Base.
* Images are generated at fixed sizes, 32×32 for Nano and 256×256 for Base. Do not expect higher resolutions from these models.
* Usage limits and billing are not yet documented. See [Access and Pricing](https://github.com/bhavy2908/dataai_docs/tree/main/product/pricing.md).

## What the console runs on

The models served in the console run on GPUs. Quantaria models do not run on quantum computers today. Quantum layers are tested on simulators and small hardware experiments, and appear in production models only where real hardware supports them. See [Quantum Path](https://github.com/bhavy2908/dataai_docs/tree/main/architecture/quantum-path.md).

## Not yet covered here

> **TODO (Quantaria team):** document account creation and sign-in options, usage limits, data handling and retention for prompts and outputs, and the console's interface controls (for example generation settings).

## Related

* [Models](/models.md)
* [Access and Pricing](https://github.com/bhavy2908/dataai_docs/tree/main/product/pricing.md)
* [Roadmap](/roadmap.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/quantaria-console.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.