# Mobile optimization

En PP OCRv4 Mobile Rec
Apache-2.0
An ultra-lightweight English text line recognition model developed by the PaddleOCR team, supporting the recognition of English and numeric characters
Text Recognition Supports Multiple Languages
E
PaddlePaddle
303
0
Korean PP OCRv3 Mobile Rec
Apache-2.0
An ultra-lightweight Korean text line recognition model that supports the recognition of Korean and numeric characters, with an average accuracy of 60.21%.
Text Recognition Supports Multiple Languages
K
PaddlePaddle
277
0
Cyrillic PP OCRv3 Mobile Rec
Apache-2.0
An ultra-lightweight Cyrillic text line recognition model developed by the PaddleOCR team, trained based on PP-OCRv3_mobile_rec and specifically optimized for Cyrillic script.
Text Recognition Supports Multiple Languages
C
PaddlePaddle
312
0
En PP OCRv3 Mobile Rec
Apache-2.0
An ultra-lightweight English text line recognition model developed by the PaddleOCR team, supporting the recognition of English and digital characters
Text Recognition Supports Multiple Languages
E
PaddlePaddle
253
0
PP OCRv5 Mobile Rec
Apache-2.0
PP-OCRv5_mobile_rec is the latest generation of text line recognition model developed by the PaddleOCR team. It supports the recognition of four languages: Simplified Chinese, Traditional Chinese, English, and Japanese, and is suitable for various complex text scenarios.
Text Recognition Supports Multiple Languages
P
PaddlePaddle
499
0
Smollm 135M Instruct
Apache-2.0
A lightweight instruction fine-tuned language model optimized for mobile deployment
Large Language Model
S
litert-community
131
1
Coreml Depth Anything V2 Small
Apache-2.0
Depth Anything V2 is a depth estimation model based on the DPT architecture, utilizing a DINOv2 backbone network. It achieves fine and robust depth prediction through training on large-scale synthetic and real-world data.
3D Vision
C
apple
67
58
Coreml YOLOv3
MIT
YOLOv3 is an efficient object detection model capable of real-time localization and classification of 80 different objects in images.
Object Detection
C
apple
53
15
Mobileclip B OpenCLIP
MobileCLIP-B is an efficient image-text model that achieves fast inference through multimodal reinforcement training and excels in zero-shot image classification tasks.
Text-to-Image
M
apple
715
3
Mobileclip S2 OpenCLIP
MobileCLIP-S2 is an efficient text-image model that achieves fast zero-shot image classification through multimodal reinforcement training.
Text-to-Image
M
apple
99.74k
6
Mobileclip S0 Timm
MobileCLIP-S0 is an efficient image-text model achieved through multimodal reinforcement training, significantly improving speed and size efficiency while maintaining high performance.
Text-to-Image
M
apple
532
10
Coreml Depth Anything Small
Apache-2.0
Depth Anything is a depth estimation model based on the DPT architecture and DINOv2 backbone network, trained on approximately 62 million images, achieving state-of-the-art results in relative and absolute depth estimation tasks.
3D Vision
C
apple
51
36
Mobileclip S2
Other
MobileCLIP S2 is a lightweight vision-language model focused on image feature extraction and zero-shot image classification tasks.
Text-to-Image Transformers
M
Xenova
86
2
Mobileclip S0
Other
MobileCLIP S0 is an ONNX adaptation of Apple's ml-mobileclip project, a zero-shot image classification model optimized for mobile devices.
Text-to-Image Transformers
M
Xenova
295
1
Plant Disease Detection Project
Other
MobileNet V2 is a lightweight convolutional neural network designed for mobile devices, achieving a balance between latency, model size, and accuracy.
Image Classification Transformers
P
Diginsa
242.43k
4
Mobilenet V2 0.35 96
Other
MobileNet V2 is a small, low-latency, low-power vision model specifically optimized for mobile devices
Image Classification Transformers
M
google
540
1
Mobilebert Uncased Mnli
This model is a fine-tuned version of the uncased MobileBERT model on the Multi-Genre Natural Language Inference (MNLI) task, suitable for zero-shot classification tasks.
Text Classification Transformers English
M
typeform
285
14
Mobilebert Finetuned Pos
MIT
MobileBERT is a lightweight variant of BERT, optimized for mobile devices while maintaining high performance.
Sequence Labeling Supports Multiple Languages
M
mrm8488
40.13k
8
Emo Mobilebert
A sentiment recognition model optimized based on MobileBERT architecture, specifically designed for the EmoContext dataset
Text Classification Transformers English
E
lordtt13
2,476
4
Mobilebert Uncased Finetuned Squadv1
A lightweight question-answering model based on MobileBERT, fine-tuned on the SQuAD v1.1 dataset, suitable for English Q&A tasks.
Question Answering System Transformers English
M
mrm8488
27
1
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase