> For the complete documentation index, see [llms.txt](https://langtech-bsc.gitbook.io/applied-intelligence/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://langtech-bsc.gitbook.io/applied-intelligence/readme.md).

# Welcome

The open models recommended by the Applied Intelligence team at the Barcelona Supercomputing Center: text, speech, machine translation and decision.

**Applied Intelligence** is a team within the **AI Institute** of the [Barcelona Supercomputing Center (BSC)](https://www.bsc.es/). We take the models trained at BSC and help people put them to work. BSC publishes many models; this site lists the few we recommend for each kind of task.

Every model listed here is **open**, published on [Hugging Face](https://huggingface.co/BSC-LT), and built with a strong focus on **Catalan, Spanish and the other languages of Spain**, alongside English and other European languages.

{% hint style="info" %}
Recommendations last reviewed: **November 2026**.
{% endhint %}

## Browse by category

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Text</strong></td><td>Instruction-tuned LLMs for chat, RAG, function calling and agents.</td><td><a href="https://2669349619-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FCiOhsmuRpZnoVwE6Nlp8%2Fuploads%2Fgit-blob-8f7038ac5b25d28d77c73eb1701151f1a40d2c9b%2Fcard-text.png?alt=media">card-text.png</a></td><td><a href="https://langtech-bsc.gitbook.io/applied-intelligence/models/text-models.md">Text (LLMs)</a></td></tr><tr><td><strong>Speech</strong></td><td>Speech recognition (ASR) and natural Catalan text-to-speech (TTS).</td><td><a href="https://2669349619-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FCiOhsmuRpZnoVwE6Nlp8%2Fuploads%2Fgit-blob-f2cae346a14b9dbb185e91bf7a250df5ef3c34da%2Fcard-speech.png?alt=media">card-speech.png</a></td><td><a href="https://langtech-bsc.gitbook.io/applied-intelligence/models/speech-models.md">Speech</a></td></tr><tr><td><strong>Machine translation</strong></td><td>Multilingual translation models covering the languages of Spain and Europe.</td><td><a href="https://2669349619-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FCiOhsmuRpZnoVwE6Nlp8%2Fuploads%2Fgit-blob-9c56544e4530b16694fd971ea5547ca4b93e9131%2Fcard-mt.png?alt=media">card-mt.png</a></td><td><a href="https://langtech-bsc.gitbook.io/applied-intelligence/models/machine-translation.md">Machine translation</a></td></tr><tr><td><strong>Decision</strong></td><td>Small, fast models that classify a request and decide what happens next.</td><td><a href="https://2669349619-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FCiOhsmuRpZnoVwE6Nlp8%2Fuploads%2Fgit-blob-851f1308fb9eba444b5fb42024fea812a546e6bf%2Fcard-dec.png?alt=media">card-dec.png</a></td><td><a href="https://langtech-bsc.gitbook.io/applied-intelligence/models/decision-models.md">Decision models</a></td></tr></tbody></table>

**Not sure where to start?** [Which model should I use?](https://langtech-bsc.gitbook.io/applied-intelligence/which-model.md) matches common tasks to a model, and [Using the models](https://langtech-bsc.gitbook.io/applied-intelligence/using-the-models.md) covers access, serving and hardware.

## How we choose

For each kind of task, we list the model we would point a partner to today:

* **The strongest option we have for the task**, judged on the languages of Spain. When a newer release replaces it, this site is updated. Older checkpoints stay on Hugging Face but are no longer listed.
* **Openly licensed.** You can download it and run it on your own infrastructure. Licenses differ between models, so check [Licenses](https://langtech-bsc.gitbook.io/applied-intelligence/resources/licenses.md) before a commercial deployment.
* **Documented honestly.** Each page says what the model is good at, where it is weak, and what hardware it needs.

Models marked <mark style="color:orange;">**Coming soon**</mark> aren't publicly released yet. Their pages are short previews until they are.

## Questions?

Ask on BSC's public [**Discord server**](https://discord.gg/twy3GnBCaY), where the community and BSC researchers answer questions about the models.

## Funding

The models listed here were developed at BSC within publicly funded initiatives, mainly the [ALIA](https://alia.gob.es/) project and the [Aina](https://projecteaina.cat/) project. Each model page lists its own funding and acknowledgements.

{% hint style="success" %}
Looking for the complete catalogues of models and datasets? See the [**ALIA Kit**](https://langtech-bsc.gitbook.io/alia-kit/) and the [**Aina Kit**](https://langtech-bsc.gitbook.io/aina-kit/).
{% endhint %}


---

# 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://langtech-bsc.gitbook.io/applied-intelligence/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.
