DINOv3 VITB16 CoreML FP32

CoreML conversion of facebook/dinov3-vitb16-pretrain-lvd1689m optimized for Apple Silicon.

Model Details

Base Model: facebook/dinov3-vitb16-pretrain-lvd1689m
Framework: CoreML
Precision: FP32
Input Size: 448×448
Model Size: 327.3 MB

Usage

Python (CoreML)

import coremltools as ct
import numpy as np
from PIL import Image

# Load model
model = ct.models.MLModel("dinov3_vitb16_448x448_fp32.mlpackage")

# Prepare image
image = Image.open("image.jpg").resize((448, 448))

# Extract features
output = model.predict({"image": image})
features = output["features"]  # Shape: [1, embed_dim, grid_size, grid_size]

Swift/iOS

import CoreML

// Load model
guard let model = try? MLModel(contentsOf: modelURL) else {
    fatalError("Failed to load model")
}

// Prepare image
guard let image = UIImage(named: "image.jpg") else {
    fatalError("Failed to load image")
}

// Extract features
let input = try MLFeatureValue(image: image.cgImage!)
let output = try model.prediction(from: [input])
let features = output.featureValue(for: "features")?.multiArrayValue

Performance

Performance metrics on Apple Silicon:

CoreML Performance

Throughput: 10.92 FPS
Latency: 91.55 ± 2.77 ms
Min Latency: 84.81 ms
Max Latency: 96.56 ms

Speedup vs PyTorch

PyTorch: 7.65 FPS
CoreML: 10.92 FPS
Speedup: 1.43x faster ⚡

Feature Accuracy

Cosine Similarity: 0.9846 (vs PyTorch)
Correlation: 0.9846
Quality: ⭐⭐⭐ Very Good - Excellent similarity

Model Specifications

Precision: FP32
Input Size: 448×448
Model Size: 327.3 MB

License

This model is released under the DINOv3 License. See LICENSE.md for details.

Citation

@article{dinov3,
  title={DINOv3: A Versatile Vision Foundation Model},
  author={Meta AI Research},
  journal={arXiv preprint arXiv:2508.10104},
  year={2025}
}

Reference: DINOv3 Paper

Key contributions:

Gram anchoring strategy for high-quality dense feature maps
Self-supervised learning on 1.689B images
Superior performance on dense vision tasks
Versatile across tasks and domains without fine-tuning

Demo Images

Input Image

*Sample input image for feature extraction demonstration*

Feature Visualization

The visualization shows:

PCA projection of high-dimensional features (RGB visualization)
Feature channel activations showing spatial patterns
Gram matrix analysis for object similarity detection
Side-by-side comparison with PyTorch reference implementation

This comprehensive visualization demonstrates that CoreML conversion preserves the semantic structure and feature quality of the original DINOv3 model.

Powered By DINOv3

🌟 This model is powered by DINOv3 🌟

Converted by Aegis AI for optimized Apple Silicon deployment.

Related Models

Original PyTorch Model: facebook/dinov3-vitb16-pretrain-lvd1689m
DINOv3 License: https://ai.meta.com/resources/models-and-libraries/dinov3-license/

Last updated: 2025-11-03

Downloads last month: 3