---
title: "Image classification"
canonical: https://docs.qvac.tether.io/sdk/v0.20/ai-capabilities/image-classification/
collection: "SDK"
package: "@qvac/sdk"
line: v0.20
current_line: false
---

# Image classification (/sdk/v0.20/ai-capabilities/image-classification)



## Overview

Image classification uses a **GGML** inference engine ([`@qvac/classification-ggml`](https://github.com/tetherto/qvac/tree/main/packages/classification-ggml)). Load a model using `modelType: "classification"`. The addon ships with a bundled MobileNetV3-Small that classifies images into three labels — `"food"`, `"report"`, and `"other"` — so no `modelSrc` and no model download are required out of the box. Custom GGUF classifiers are supported by passing your own `modelSrc`.

Provide an image to `classify()` as a `Uint8Array` of either:

* an encoded **JPEG or PNG** buffer; or
* **raw RGB** bytes, alongside `width`, `height`, and `channels: 3`.

`classify()` returns `ClassificationResult[]` — an array of `{ label, confidence }` entries sorted by confidence in descending order. Use `topK` to limit the number of results returned, either as a load-time default (`modelConfig.topK`) or as a per-call override.

## Functions

Use the following sequence of function calls:

1. [`loadModel()`](/sdk/v0.20/reference/api#loadmodel)
2. [`classify()`](/sdk/v0.20/reference/api#classify)
3. [`unloadModel()`](/sdk/v0.20/reference/api#unloadmodel)

For how to use each function, see [SDK — API reference](/sdk/v0.20/reference/api/).

## Models

Supported model families and their file layouts:

* **MobileNetV3-Small**: single all-in-one `*.gguf` file — the base model or any fine-tune of the same architecture (converted to GGUF). Fine-tunes may define their own classes and labels; the label set is sourced from the GGUF metadata.

For models available as constants, see [SDK — Models](/sdk/v0.20/#models).

<Callout type="info">
  **Default model:** alternatively, you can load no model at all. In that case the base **MobileNetV3-Small** classifier is loaded automatically — no `modelSrc` and no download required. It emits the following fixed labels: `"food"`, `"report"`, and `"other"`.
</Callout>

## Example

The following script classifies a JPEG image using the bundled MobileNetV3-Small model:

<Tabs>
  <Tab value="js" label="JavaScript" default>
    <WrapCode>
      ```js file=<rootDir>/packages/sdk/dist/examples/classification/classify-image.js title="classify-image.js" lineNumbers
      import fs from 'fs';
      import { loadModel, classify, unloadModel } from '@qvac/sdk';
      /**
       * Classify an image using the bundled MobileNetV3-Small model.
       *
       * The bundled model produces three classes: "food", "report", "other".
       * No modelSrc is needed — the model ships inside @qvac/classification-ggml.
       */
      async function main() {
          const modelId = await loadModel({
              modelType: 'ggml-classification'
          });
          const image = fs.readFileSync('image.jpg');
          const results = await classify({ modelId, image });
          console.log('Classification results:');
          for (const { label, confidence } of results) {
              console.log(`  ${label}: ${(confidence * 100).toFixed(1)}%`);
          }
          await unloadModel({ modelId });
      }
      main().catch(console.error);
      ```
    </WrapCode>
  </Tab>

  <Tab value="ts" label="TypeScript">
    <WrapCode>
      ```ts file=<rootDir>/packages/sdk/examples/classification/classify-image.ts title="classify-image.ts" lineNumbers
      import fs from 'fs'
      import { loadModel, classify, unloadModel } from '@qvac/sdk'

      /**
       * Classify an image using the bundled MobileNetV3-Small model.
       *
       * The bundled model produces three classes: "food", "report", "other".
       * No modelSrc is needed — the model ships inside @qvac/classification-ggml.
       */
      async function main() {
        const modelId = await loadModel({
          modelType: 'ggml-classification'
        })

        const image = fs.readFileSync('image.jpg')
        const results = await classify({ modelId, image })

        console.log('Classification results:')
        for (const { label, confidence } of results) {
          console.log(`  ${label}: ${(confidence * 100).toFixed(1)}%`)
        }

        await unloadModel({ modelId })
      }

      main().catch(console.error)
      ```
    </WrapCode>
  </Tab>
</Tabs>

<Callout type="info">
  The Python client supports this capability through the same worker. A dedicated Python example is not yet published — see the [Python SDK](/sdk/v0.20/python-sdk) for the API surface.
</Callout>

<Callout type="success">
  **Tip:** all examples throughout this documentation are self-contained and runnable. For instructions on how to run them, see the [JS/TS quickstart](/sdk/v0.20/js-ts-sdk#quickstart) or the [Python quickstart](/sdk/v0.20/python-sdk#quickstart).
</Callout>