YOLO26m-OptiQ-6bit

YOLO26m-OptiQ-6bit

Mixed-precision quantized YOLO26m for Apple Silicon via optiq

This is a mixed-precision quantized version of YOLO26m in MLX format, optimized with mlx-optiq for Apple Silicon inference via yolo-mlx.

Quantization Details

Benchmark Results (COCO128)

Detection delta: +1 (+0.1%) at 4.4x compression.

Usage

Requires mlx-optiq and yolo-mlx:

pip install mlx-optiq yolo-mlx

from optiq.models.yolo import load_quantized_yolo

model = load_quantized_yolo("mlx-community/YOLO26m-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.

Article

For more details on the methodology and results, see: Not All Layers Are Equal

Credits

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