alibaba/MNN

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

93
/ 100
Verified

Supports inference and training across multiple frameworks (TensorFlow, Caffe, ONNX, TorchScript) with specialized runtimes for LLMs via MNN-LLM and diffusion models via MNN-Diffusion. Employs aggressive optimization strategies including FP16/Int8 quantization (50-70% size reduction), minimal dependencies, and platform-specific backends to achieve sub-2MB executable overhead on iOS and 800KB core library on Android. Integrates with MNN Workbench for model visualization and one-click deployment across mobile, embedded, and IoT devices.

14,526 stars and 220,239 monthly downloads. Actively maintained with 77 commits in the last 30 days. Available on PyPI.

Maintenance 25 / 25
Adoption 20 / 25
Maturity 25 / 25
Community 23 / 25

How are scores calculated?

Stars

14,526

Forks

2,234

Language

C++

License

Apache-2.0

Last pushed

Mar 13, 2026

Monthly downloads

220,239

Commits (30d)

77

Dependencies

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/alibaba/MNN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.