# Axelera AI

Models are located at the [Axelera AI model zoo on the AI Hub](https://hub.degirum.com/public-models/degirum/axelera?utm_source=docs.degirum.com\&utm_medium=site\&utm_campaign=ai-hub-public-models-axelera-ai).

## Models by DeGirum

### Axelera Metis

**Detection**

| Model Name                                                         | Use Case                                      | mAP 50‑95                              | mAP 50                                 |
| ------------------------------------------------------------------ | --------------------------------------------- | -------------------------------------- | -------------------------------------- |
| yolov8n\_coco--640x640\_quant\_axelera\_metis\_1                   | COCO Detection                                | 0.3561                                 | 0.5059                                 |
| yolov8n\_coco\_seg--640x640\_quant\_axelera\_metis\_1              | COCO Instance Segmentation                    | <p>bbox: 0.3510</p><p>mask: 0.2940</p> | <p>bbox: 0.5015</p><p>mask: 0.4706</p> |
| yolov8l\_coco--640x640\_quant\_axelera\_metis\_1                   | COCO Detection                                | 0.5140                                 | 0.6853                                 |
| yolov8m\_coco--640x640\_quant\_axelera\_metis\_1                   | COCO Detection                                | 0.4825                                 | 0.6531                                 |
| yolov8s\_coco--640x640\_quant\_axelera\_metis\_1                   | COCO Detection                                | 0.4375                                 | 0.6053                                 |
| yolov9t\_coco--640x640\_quant\_axelera\_metis\_1                   | COCO Detection                                | 0.3665                                 | 0.5119                                 |
| yolov8n\_coco\_pose--640x640\_quant\_axelera\_metis\_1             | COCO Pose Keypoints                           | <p>bbox: 0.5160</p><p>kpts: 0.4838</p> | <p>bbox: 0.7059</p><p>kpts: 0.7894</p> |
| yolov8n\_relu6\_face--640x640\_quant\_axelera\_metis\_1            | Face Detection                                | 0.5645                                 | 0.7834                                 |
| yolov8n\_relu6\_hand--640x640\_quant\_axelera\_metis\_1            | Hand Detection                                | 0.4453                                 | 0.7550                                 |
| yolov8n\_relu6\_person--640x640\_quant\_axelera\_metis\_1          | Person Detection                              | 0.3119                                 | 0.4993                                 |
| yolov8n\_relu6\_ppe--640x640\_quant\_axelera\_metis\_1             | Personal Protective Equipment (PPE) Detection | 0.3548                                 | 0.6778                                 |
| yolov8n\_relu6\_lp--640x640\_quant\_axelera\_metis\_1              | License Plate Detection                       | 0.5611                                 | 0.8586                                 |
| yolov8n\_relu6\_face\_kpts--640x640\_quant\_axelera\_metis\_1      | Face Detection with Keypoints                 | <p>bbox: 0.2809</p><p>kpts: 0.3885</p> | <p>bbox: 0.3600</p><p>kpts: 0.4504</p> |
| yolov8n\_dota\_obb--1024x1024\_quant\_axelera\_metis\_1            | OBB Detection                                 | 0.4543                                 | 0.6016                                 |
| yolov8n\_relu6\_widerface\_kpts--640x640\_quant\_axelera\_metis\_1 | Face Detection with Five Keypoints            | <p>bbox: 0.2607</p><p>kpts: 0.2317</p> | <p>bbox: 0.7981</p><p>kpts: 0.5391</p> |
| yolov8n\_relu6\_fire\_smoke--640x640\_quant\_axelera\_metis\_1     | Fire & Smoke Detection                        | 0.4155                                 | 0.7383                                 |
| yolo11n\_coco--640x640\_quant\_axelera\_metis\_1                   | COCO Detection                                | 0.3853                                 | 0.5422                                 |
| yolo11n\_coco\_pose--640x640\_quant\_axelera\_metis\_1             | COCO Pose Keypoints                           | <p>bbox: 0.5104</p><p>kpts: 0.4642</p> | <p>bbox: 0.6912</p><p>kpts: 0.7947</p> |
| yolo11n\_coco\_seg--640x640\_quant\_axelera\_metis\_1              | COCO Instance Segmentation                    | <p>bbox: 0.3790</p><p>mask: 0.3099</p> | <p>bbox: 0.5316</p><p>mask: 0.4977</p> |

**Classification**

| Model Name                                                          | Use Case              | Top‑1  | Top‑5 |
| ------------------------------------------------------------------- | --------------------- | ------ | ----- |
| yolov8n\_relu6\_fairface\_gender--256x256\_quant\_axelera\_metis\_1 | Gender Classification | 92.93% | 100%  |


---

# Agent Instructions: 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.degirum.com/ai-hub/public-models/axelera-ai.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.