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: yolo26s-mlx
results:
- task:
type: object-detection
name: Object Detection
dataset:
name: COCO val2017
type: coco
metrics:
- type: mAP
value: 0.476
name: mAP@0.5:0.95
YOLO26s (MLX)
Pure-MLX weights for YOLO26s, ready to run on Apple Silicon with
yolo-mlx. No PyTorch at runtime,
no cloud calls, no waiting on someone else's API — everything stays on your Mac.
This is the balanced default in the YOLO26 MLX family: a solid mix of accuracy and speed for most use cases.
Quickstart
pip install yolo-mlx huggingface_hub
from huggingface_hub import hf_hub_download
from yolo26mlx import YOLO
weights = hf_hub_download("webAI-Official/yolo26s-mlx", "yolo26s.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 |
|---|---|---|---|
| yolo26s | 47.6% | 105 | Balanced default |
Other variants in this family:
yolo26n-mlx ·
yolo26m-mlx ·
yolo26l-mlx ·
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 |
|---|---|
yolo26s.npz |
MLX-format weights, converted from the YOLO26s .pt checkpoint and verified shape-by-shape against the source. |
README.md |
This card. |
Training data
Pretrained on COCO (80 classes). For domain-specific use cases, fine-tune on your own data — see the training guide in the upstream repo.
License
AGPL-3.0, inherited from upstream
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 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 · 💬 community.webai.com