YOLO26n-OptiQ-6bit – AI Model by mlx-community | AlphaNeural AI

You can deploy this model and start earning money today!

mlx-community/
YOLO26n-OptiQ-6bit

like

0

mixed-precision

object-detection

Ultralytics/YOLO26

Views

No views yet

YOLO26n-OptiQ-6bit

Mixed-precision quantized YOLO26n for Apple Silicon via optiq

This is a mixed-precision quantized version of YOLO26n in MLX format, optimized with mlx-optiq for Apple Silicon inference via yolo-mlx.

Quantization Details

Property	Value
Target BPW	6.0
Achieved BPW	5.96
Layers at 4-bit	12
Layers at 8-bit	114
Original size	9.9 MB
Quantized size	2.5 MB
Compression	3.9x

Benchmark Results (COCO128)

Model	Total Detections	Avg/Image
optiq 6-bit	548	4.3
Original (FP32)	557	4.4

Detection delta: -9 (-1.6%) at 3.9x compression.

Usage

Requires mlx-optiq and yolo-mlx:

pip install mlx-optiq yolo-mlx

python

from optiq.models.yolo import load_quantized_yolo

model = load_quantized_yolo("mlx-community/YOLO26n-OptiQ-6bit")
results = model.predict("image.jpg")

How optiq Works

optiq measures each conv layer's sensitivity via KL divergence on detection outputs, then assigns optimal per-layer bit-widths using greedy knapsack optimization. Sensitive layers (detection head, feature pyramid) get 8-bit precision while robust backbone layers get 4-bit.

Credits

Quantization: mlx-optiq
Base model: YOLO26 by Ultralytics
MLX runtime: yolo-mlx
Framework: MLX by Apple