Tencent/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
This framework helps mobile app developers integrate high-performance artificial intelligence features into their applications. It takes pre-trained deep learning models and optimizes them to run efficiently on mobile phone CPUs, enabling intelligent functionalities directly on users' devices. The end-user persona for this project is a mobile application developer.
22,890 stars. Actively maintained with 31 commits in the last 30 days.
Use this if you are a mobile app developer looking to deploy deep learning models to iOS, Android, or HarmonyOS devices with excellent performance and no third-party dependencies.
Not ideal if you are looking for a tool to train deep learning models or deploy them on desktop or server-side infrastructure.
Stars
22,890
Forks
4,405
Language
C++
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
31
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Tencent/ncnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
OpenMined/TenSEAL
A library for doing homomorphic encryption operations on tensors
iree-org/iree-turbine
IREE's PyTorch Frontend, based on Torch Dynamo.
uxlfoundation/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
apache/tvm
Open Machine Learning Compiler Framework
VeriSilicon/TIM-VX
VeriSilicon Tensor Interface Module