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

# Home

An inference server for open language models, with its own engine, GPU kernels and compressed weight formats, behind an OpenAI-compatible API.

{% hint style="info" %}
NVCL AI is in beta and free for personal use, with a free NVCL AI account: one install line sets it up. NVCL AI, its installer and these docs are updated all the time, and any feedback is welcome.
{% endhint %}

<a href="/overview/request-access.md" class="button primary">Get NVCL AI</a> <a href="/get-started/requirements.md" class="button secondary">Get started</a>

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><i class="fa-circle-info">:circle-info:</i></td><td><strong>What it is</strong></td><td>What NVCL AI is, what it does well and who it is for.</td><td><a href="/overview/what-it-is.md">What it is</a></td></tr><tr><td><i class="fa-chart-line">:chart-line:</i></td><td><strong>Performance at a glance</strong></td><td>NVCL AI against vLLM and SGLang, in plain words.</td><td><a href="/overview/performance.md">Performance at a glance</a></td></tr><tr><td><i class="fa-terminal">:terminal:</i></td><td><strong>Get started</strong></td><td>Requirements, install, the first request.</td><td><a href="/get-started/requirements.md">Requirements</a></td></tr><tr><td><i class="fa-lightbulb">:lightbulb:</i></td><td><strong>Concepts</strong></td><td>Why it is fast and why quality holds.</td><td><a href="/concepts/why-fast.md">Why it is fast</a></td></tr><tr><td><i class="fa-gauge-high">:gauge-high:</i></td><td><strong>Benchmarks</strong></td><td>Full tables with the conditions of every run.</td><td><a href="/benchmarks/benchmarks.md">How to read the tables</a></td></tr><tr><td><i class="fa-book">:book:</i></td><td><strong>Reference</strong></td><td>Models, GPUs, weight formats, API, monitoring.</td><td><a href="/reference/models.md">Supported models</a></td></tr></tbody></table>