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

# Welcome to XYNQ

XYNQ is a **distributed inference network** that delivers frontier-grade AI to anyone, for free, with no account required and no conversation ever stored.

Instead of renting centralized data-center clusters, XYNQ pools the idle GPUs of its community into a single elastic supercomputer. When you send a prompt, it is sharded across volunteer nodes around the world, executed in parallel, and streamed back to your terminal — usually within a fraction of a second of scheduling overhead.

> **Free compute, forever.** The more people who connect their hardware, the more capacity the network has, and the more people it can serve at no cost.

### Why XYNQ exists

Modern AI is gated behind three barriers: **cost**, **accounts**, and **surveillance**. Most assistants make you sign up, log your conversations, and eventually pay. XYNQ was built to remove all three:

* **No cost** — inference runs on donated, otherwise-idle GPU cycles.
* **No sign-ups** — open the terminal and start typing. No email, no wallet, no profile.
* **No memory** — conversations live only in your browser tab and are destroyed on refresh.

### What you can do

* Chat with capable open and in-house models directly from the XYNQ terminal.
* Switch between models such as **Jaguar**, **Qwen 3.5 27B**, and **SuperGemma 4 26B**.
* Contribute your own GPU to the mesh and earn $XYNQ.
* Watch the network's live telemetry — node count, aggregate VRAM, and real-time utilization.

### How this documentation is organized

| Section            | What's inside                                    |
| ------------------ | ------------------------------------------------ |
| Overview           | The vision, the network model, and key features. |
| Getting Started    | Send your first prompt in under a minute.        |
| Architecture       | How the mesh, scheduler, and sharding work.      |
| Models             | The model catalog and per-model details.         |
| Contribute Compute | Turn your idle GPU into a network node.          |
| Privacy            | Our zero-retention and no-account guarantees.    |
| XYNQ Token         | How $XYNQ funds and sustains the network.        |
| Reference          | FAQ, glossary, and roadmap.                      |


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.xynq.ai/welcome-to-xynq.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.