> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nexa.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Get started with NexaSDK Docker on Linux ARM64 in minutes.

## **Tutorial Video**

<iframe className="w-full aspect-video rounded-xl" src="https://www.youtube.com/embed/auxoXSeMVsg" title="SDK for Linux Tutorial" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowFullScreen />

## **Installation**

### **Pull Docker Image**

Pull the latest NexaSDK Docker image from Docker Hub:

```bash bash theme={"dark"}
docker pull nexa4ai/nexasdk:latest
```

## **Usage Modes**

NexaSDK Docker supports two usage modes: server mode for REST API access and interactive CLI mode for direct model inference.

### **CLI Mode (Interactive)**

Run NexaSDK in interactive CLI mode for direct model inference:

```bash bash theme={"dark"}
export NEXA_TOKEN="YOUR_LONG_TOKEN_HERE"
docker run --rm -it --privileged \
  -v /path/to/data:/data \
  -v /etc/machine-id:/etc/machine-id:ro \
  -e NEXA_TOKEN \
  nexa4ai/nexasdk:latest infer NexaAI/Granite-4.0-h-350M-NPU
```

<Note>
  The `-it` flags enable interactive mode. Replace `NexaAI/Granite-4.0-h-350M-NPU` with any supported model name. For a complete list of supported models, see the [Overview](/en/nexa-sdk-docker/overview#supported-models) page.
</Note>

### **Server Mode (Detached)**

Run NexaSDK in server mode to expose a REST API endpoint. This mode runs in the background:

```bash bash theme={"dark"}
export NEXA_TOKEN="YOUR_LONG_TOKEN_HERE"
docker run --rm -it --privileged \
  -v /path/to/data:/data \
  -v /etc/machine-id:/etc/machine-id:ro \
  -e NEXA_TOKEN \
  nexa4ai/nexasdk:latest pull [MODEL_NAME]
docker run --rm -d -p 18181:18181 --privileged \
  -v /path/to/data:/data \
  -v /etc/machine-id:/etc/machine-id:ro \
  -e NEXA_TOKEN \
  nexa4ai/nexasdk:latest serve
```

<Note>
  The `--privileged` flag is required for NPU access. Replace `YOUR_LONG_TOKEN_HERE` with your actual Nexa token. You can obtain a token by creating an account at [sdk.nexa.ai](https://sdk.nexa.ai) and generating one in **Deployment → Create Token**.
</Note>

`nexa serve` won't auto download models. Make sure to pre-download the models you intend to use.

The server will be accessible at `http://localhost:18181`. For detailed API documentation, see the [REST API](/en/nexa-sdk-docker/RestAPI) page.

## **Next Steps**

<CardGroup cols={2}>
  <Card title="REST API" href="/en/nexa-sdk-docker/RestAPI" icon="code">
    Learn how to use the REST API endpoints for chat completions, embeddings, reranking, and more.
  </Card>

  <Card title="NPU Models" href="/en/nexa-sdk-go/npu" icon="microchip">
    Explore the full collection of NPU-optimized models available for Qualcomm devices.
  </Card>
</CardGroup>

<br />

<div class="feedback-wrapper">
  <span class="feedback-label">Was this page helpful?</span>

  <div class="feedback-toggle">
    <input type="radio" name="feedback" id="feedback-yes" class="feedback-input" />

    <label for="feedback-yes" class="feedback-button">
      <img src="https://mintcdn.com/nexaai/g8-zBYnunEyVtcK3/Images/FeedBack/thumbs-up.svg?fit=max&auto=format&n=g8-zBYnunEyVtcK3&q=85&s=0b57c51c8db9940403e7552956e5c30e" alt="Thumbs up" class="feedback-icon" noZoom width="14" height="14" data-path="Images/FeedBack/thumbs-up.svg" />

      Yes
    </label>

    <input type="radio" name="feedback" id="feedback-no" class="feedback-input" />

    <label for="feedback-no" class="feedback-button">
      <img src="https://mintcdn.com/nexaai/g8-zBYnunEyVtcK3/Images/FeedBack/thumbs-down.svg?fit=max&auto=format&n=g8-zBYnunEyVtcK3&q=85&s=ebacf61d57c8259c6df243d329b548b3" alt="Thumbs down" class="feedback-icon" noZoom width="14" height="14" data-path="Images/FeedBack/thumbs-down.svg" />

      No
    </label>
  </div>
</div>
