> 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/product/features.md).

# Features

A summary of what Quantaria models offer today and what is planned. Capabilities marked **live** are available on the [Quantaria Console](https://github.com/bhavy2908/dataai_docs/tree/main/overview/quantaria-console.md).

## Live today

| Feature                   | Detail                                                        | Status |
| ------------------------- | ------------------------------------------------------------- | ------ |
| Text generation           | Hilbert-1 Nano (2K-token context) and Base (8K-token context) | Live   |
| Image generation          | Hilbert-1 Nano (32×32) and Base (256×256)                     | Live   |
| One model, two modalities | Text and images from one shared tensor-network backbone       | Live   |
| Two sizes                 | \~100M parameters (Nano) and \~1B parameters (Base)           | Live   |

## Architecture features

* **Tensor-network weights from the first training step.** No dense model is compressed after the fact. See [Tensor-Network Weights](https://github.com/bhavy2908/dataai_docs/tree/main/architecture/tensor-network-weights.md).
* **Tensor Product Attention.** A factorized attention scheme with a smaller KV cache. Basis: [arXiv:2501.06425](https://arxiv.org/abs/2501.06425).
* **MPO mixture-of-experts (Hilbert-1 Base).** Experts share a central tensor. Basis: [arXiv:2203.01104](https://arxiv.org/abs/2203.01104).
* **Rank-adaptive bond dimensions.** χ shrinks or grows during training. Basis: [arXiv:2405.14377](https://arxiv.org/abs/2405.14377).
* **Canonical-form gauging.** Numerically stable contraction.

## Planned and research

| Feature         | Detail                                                         | Status   |
| --------------- | -------------------------------------------------------------- | -------- |
| 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 on simulators, then cloud QPUs | Research |
| Born            | Born-machine generative heads                                  | Research |

## Evaluation commitments

* Every model is compared with a dense transformer of the same size on the same data.
* Metrics: loss curves, perplexity, FID and memory use.
* Results are published whether or not they favour the tensor-network model.

> **TODO (Quantaria team):** add API, SDK or developer-access features here once they exist and are documented.

See [How It Works](/product/how-it-works.md) for the execution flow and [Models](https://github.com/bhavy2908/dataai_docs/tree/main/overview/models.md) for specs.


---

# 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/product/features.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.