E

Efficientformer L3 300

Developed by snap-research
EfficientFormer-L3 is a lightweight vision Transformer model developed by Snap Research, optimized for mobile devices to achieve low latency while maintaining high performance.
Downloads 279
Release Time : 1/7/2023

Model Overview

This model is part of the EfficientFormer series, featuring a well-designed Transformer architecture for efficient image classification tasks on mobile devices.

Model Features

Mobile Optimization
Designed specifically for mobile devices, achieving low-latency inference of 3ms on devices like iPhone 12
High Performance
Achieves 82.4% Top-1 accuracy on the ImageNet-1K dataset
Efficient Architecture
Utilizes dimension-consistent design and 4D blocks with CONV-BN fusion for efficient inference

Model Capabilities

Image Classification
Semantic Segmentation

Use Cases

Computer Vision
Mobile Image Classification
Perform real-time image classification tasks on mobile devices like smartphones
Achieves 3ms low latency on iPhone 12
Smart Photo Album Management
Automatically categorize photo content in albums
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase