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

# README

**Quantaria** is a research company building multimodal generative models whose weights are tensor networks (matrix product states and operators, MPS/MPO) from the first training step. One shared backbone generates both text and images. Because the weights use the same format physicists use to describe quantum states, individual layers have a direct path from GPUs to quantum hardware as that hardware matures.

Website: [quantaria.xyz](https://quantaria.xyz) | Console: [console.quantaria.xyz](https://console.quantaria.xyz) | Contact: <hello@quantaria.xyz>

{% hint style="info" %}
**Status.** Hilbert-1 Nano (\~100M parameters) and Hilbert-1 Base (\~1B parameters) are live on the [Quantaria Console](/overview/quantaria-console.md). Quantaria models train and run on GPUs today. They do not run on quantum computers.
{% endhint %}

## Models at a glance

| Model               | What it is                                                                | Status              |
| ------------------- | ------------------------------------------------------------------------- | ------------------- |
| **Hilbert-1 Nano**  | \~100M parameters, 2K-token text context, 32×32 image output              | Live on the console |
| **Hilbert-1 Base**  | \~1B parameters, 8K-token context, 256×256 images, MPO mixture-of-experts | Live on the console |
| **Hilbert-1 Large** | Scale set after Base results                                              | Planned             |
| **Schmidt**         | Compact text model for long context on laptops and phones                 | Planned             |
| **Bond**            | Open-source PyTorch library behind every model                            | Planned             |
| **Dirac**           | Hybrid quantum-classical layers                                           | Research            |
| **Born**            | Born-machine generative heads                                             | Research            |

## What makes Quantaria different

* **Tensor networks from step zero.** Every layer is trained natively as an MPS or MPO. Nothing is compressed from a dense model afterwards.
* **One backbone, two modalities.** A Transfusion-style objective trains next-token loss on text and diffusion loss on image patches over one set of shared tensor cores.
* **A path to quantum hardware.** A bond of dimension χ carries a bounded amount of entanglement, which maps onto circuits that quantum processors can run. Quantum layers ship in production models only where real hardware supports them.
* **Honest numbers.** Figures in these docs come from published papers on the methods Quantaria combines, not from Quantaria's own models. Each one links to its source.

## Explore the documentation

* [Quantaria Overview](/overview/quantaria-overview.md): the approach in one page
* [Models](/overview/models.md): every model line and its status
* [Quantaria Console](/overview/quantaria-console.md): where to use Hilbert-1 today
* [Getting Started](/guides/getting-started.md): generate your first text and image
* [How It Works](/product/how-it-works.md): from tensor cores to generated output
* [Tensor-Network Weights](/architecture/tensor-network-weights.md): MPS, MPO, bond dimension, Schmidt truncation
* [Quantum Path](/architecture/quantum-path.md): what runs where, and what is still research
* [Research Foundations](/architecture/research-foundations.md): the papers behind the approach
* [Roadmap](/overview/roadmap.md) and [FAQ](/reference/faq.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.nerve-protocol.com/readme.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.