local-ai

MNN: Fast On-Device AI

Name: MNN: Fast On-Device AI
Author: alibaba

Get high-performance Edge AI with MNN, battle-tested by Alibaba, for startup founders, with 15k+ GitHub stars

15,386 stars2,340 forksC++Quality 9/10Updated 6/3/2026100% free · open source

About this skill

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

Topics

arm

convolution

deep-learning

embedded-devices

llm

machine-learning

mnn

transformer

vulkan

winograd-algorithm

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

321.1M

repo size

Apache-2.0

license

Key files

.pre-commit-config.yaml

AGENTS.md

README_CN.md

README_JP.md

README_TW.md

README.md

File tree

.github/

.pre-commit-hooks/

3rd_party/

apps/

backupcode/

benchmark/

ciscripts/

cmake/

codegen/

demo/

doc/

docs/

express/

include/

package_scripts/

project/

pymnn/

resource/

schema/

skills/

source/

test/

tools/

transformers/

Quick Actions

Details

Creator

alibaba

Language

C++

Related skills

More local-ai tools founders pair with this one.

local-ai★ 115,047

Run LLMs with llama.cpp

Get fast LLM inference with llama.cpp, for founders using C++.

local-ai★ 218

Xybrid: AI on-device

Build AI-powered apps with Xybrid, for startup founders, with on-device AI capabilities.