> 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/hardware-requirements.md).

# Hardware Requirements

You don't need a data-center GPU to contribute — consumer cards are exactly what the network is built on.

### Minimum

| Component | Minimum                                         |
| --------- | ----------------------------------------------- |
| GPU       | Modern NVIDIA GPU with ≥ 8 GB VRAM              |
| VRAM      | 8 GB (more VRAM → larger shards → more rewards) |
| RAM       | 16 GB system memory                             |
| Network   | Stable broadband; low latency helps             |
| OS        | Windows, Linux, or macOS (supported builds)     |

### Recommended

| Component | Recommended                     |
| --------- | ------------------------------- |
| GPU       | RTX 3080 / 4070 Ti / 4090 class |
| VRAM      | 12–24 GB                        |
| Network   | Wired connection, low jitter    |

### How capability maps to contribution

* **VRAM** determines how large a shard your node can hold. More VRAM means it can host bigger stages (and earn more).
* **Compute (TFLOPS)** determines how fast your node clears its assigned work.
* **Network latency** affects how often the router includes your node in low-latency pipelines.

### Reference fleet

The current reference fleet illustrates the range of useful hardware:

| GPU         | VRAM       | Approx. FP32 compute |
| ----------- | ---------- | -------------------- |
| RTX 3080 ×2 | 10 GB each | \~29.8 TFLOPS each   |
| RTX 4070 Ti | 12 GB      | \~40.1 TFLOPS        |
| RTX 4090 ×2 | 24 GB each | \~82.6 TFLOPS each   |

Every card helps. Lighter GPUs make excellent middle-pipeline shard hosts; heavier GPUs carry the largest stages.


---

# 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/hardware-requirements.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.