README.md

---
license: agpl-3.0
library_name: mlx
tags:
  - object-detection
  - yolo
  - yolo26
  - mlx
  - apple-silicon
  - on-device
  - edge
pipeline_tag: object-detection
datasets:
  - coco
model-index:
  - name: yolo26m-mlx
    results:
      - task:
          type: object-detection
          name: Object Detection
        dataset:
          name: COCO val2017
          type: coco
        metrics:
          - type: mAP
            value: 0.523
            name: mAP@0.5:0.95
---

# YOLO26m (MLX)

Pure-MLX weights for **YOLO26m**, ready to run on Apple Silicon with
[`yolo-mlx`](https://github.com/thewebAI/yolo-mlx). No PyTorch at runtime,
no cloud calls, no waiting on someone else's API — everything stays on your Mac.

This is a mid-size variant in the YOLO26 MLX family: higher accuracy than n/s while still fast enough for many real-time use cases.

## Quickstart

```bash
pip install yolo-mlx huggingface_hub
```

```python
from huggingface_hub import hf_hub_download
from yolo26mlx import YOLO

weights = hf_hub_download("webAI-Official/yolo26m-mlx", "yolo26m.npz")
model = YOLO(weights)

results = model.predict("https://ultralytics.com/images/bus.jpg", conf=0.25)
results[0].save()
```

## Specs

| Variant | mAP@0.5:0.95 | FPS (M4 Pro) | Best for                     |
|---------|--------------|--------------|------------------------------|
| yolo26m | 52.3%        | 55          | Higher accuracy, still fast |

Other variants in this family:
[`yolo26n-mlx`](https://huggingface.co/webAI-Official/yolo26n-mlx) ·
[`yolo26s-mlx`](https://huggingface.co/webAI-Official/yolo26s-mlx) ·
[`yolo26l-mlx`](https://huggingface.co/webAI-Official/yolo26l-mlx) ·
[`yolo26x-mlx`](https://huggingface.co/webAI-Official/yolo26x-mlx)

## Requirements

- Apple Silicon Mac (M1, M2, M3, or M4)
- macOS 14.0+
- Python 3.10+

Intel Macs are not supported — the whole point of MLX is Apple Silicon native acceleration.

## What's in this repo

| File          | Description                                         |
|---------------|-----------------------------------------------------|
| `yolo26m.npz` | MLX-format weights, converted from the YOLO26m `.pt` checkpoint and verified shape-by-shape against the source. |
| `README.md`   | This card.                                          |

## Training data

Pretrained on [COCO](https://cocodataset.org/) (80 classes). For domain-specific
use cases, fine-tune on your own data — see the
[training guide](https://github.com/thewebAI/yolo-mlx/blob/main/GUIDE_TRAINING_BENCHMARK.md)
in the upstream repo.

## License

AGPL-3.0, inherited from upstream
[`thewebAI/yolo-mlx`](https://github.com/thewebAI/yolo-mlx).
Free to use, fork, modify, and ship for personal projects, research, and
prototypes. If you deploy this as a hosted service for real users, AGPL
requires you to publish your source under the same license.

## About webAI

[webAI](https://www.webai.com/) builds the sovereign AI platform — AI that runs
on your infrastructure, stays under your control, and compounds with your
knowledge. Every release here reflects a simple belief: **open models, owned
locally, coordinated intelligently, compound into something no centralized
system can match.**

🌐 [webai.com](https://www.webai.com/) · 💬 [community.webai.com](https://community.webai.com)