Shypd.aiThe largest open index of AI toolsMNN is a blazing-fast, lightweight deep learning inference engine developed by Alibaba, powering high-performance on-device LLMs and Edge AI. It supports inference and training of deep learning models with industry-leading performance.
Trending
About
MNN is a highly efficient and lightweight deep learning framework developed by Alibaba, optimized for inference and training of deep learning models on devices. It delivers industry-leading performance and has been integrated into over 30 Alibaba apps, covering more than 70 usage scenarios. MNN-LLM, built on the MNN engine, enables local deployment of large language models on mobile phones, PCs, and IoT devices, supporting models like Qianwen, Baichuan, and LLAMA. MNN-Diffusion provides a runtime solution for deploying stable diffusion models locally. Key features include its lightweight design, versatility in supporting various model formats (Tensorflow, Caffe, ONNX, Torchscripts) and architectures, and high performance achieved through optimized assembly code and GPU acceleration.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
