Open Source
MNN-LLM
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
Our verdict
We have not reviewed MNN-LLM yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About MNN-LLM
MNN is a lightweight C++ inference engine designed for on-device LLM and edge AI deployment. Built and battle-tested by Alibaba, it prioritizes speed and minimal resource footprint for running models on constrained hardware.
Best for
Developers building production on-device LLM and edge AI applications where latency and resource efficiency are critical.
Use cases
- Running LLMs on mobile and edge devices with low latency
- Deploying inference in resource-constrained environments
- Building on-device AI applications without cloud dependency
Notes
15,353 stars on GitHub. Last updated 2026-06-01. Licensed Apache-2.0.
Pros
- Lightweight footprint optimized for edge hardware
- High performance inference engine with production validation from Alibaba
- C++ foundation enables tight integration and control
Cons
- Smaller ecosystem and community compared to mainstream frameworks
- Steeper learning curve for developers unfamiliar with C++
- Limited built-in tooling for model conversion and optimization workflows
Key facts
What we have checked
- Latest version
- 3.6.2 (released 29 Oct 2026)
- Days since the last commit
- 0
- GitHub forks
- 2,529
- GitHub stars
- 16,515
- Days to a first reply on issues
- 17
- Open issues
- 43
- Releases in the last 90 days
- 1
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
Stars and usage
How MNN-LLM is growing
15,353 to 16,515
Health and security
Is MNN-LLM looked after, and what do its setup files show
Health score
78 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 30 of 30 | Last push 0 days ago |
| Releases | 7.5 of 15 | 1 release in 90 days |
| Issue replies | 9.7 of 20 | First reply in 17 days (median) |
| Maintainer | 15 of 15 | Owned by an organisation |
| Official source | Not counted | MCP servers only |
Alternatives
Alternatives to MNN-LLM
| Record | Type | How we know | Checked |
|---|---|---|---|
| llama.cppAlternative to this | Open source | Named in the listing | Not dated |
| llama.cppThis is an alternative to it | App | Named in the listing | Not dated |
| LMDeployThis is an alternative to it | Open source | Named in the listing | Not dated |
| TensorRT-LLMThis is an alternative to it | Open source | Named in the listing | Not dated |
Compare
Compare MNN-LLM side by side
Sources
Where this comes from
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
Released 3.6.2
Released 3.6.1
Released 3.6.0
Released 3.5.0
Released 3.4.1
Released 3.4.0
Released 3.3.0
Released 3.2.5
Released 3.2.4
Released 3.2.2
Released 3.2.0
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
llama.cpp
Various
LLM inference in C/C++
LMDeploy
Community
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
TensorRT-LLM
Community
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NV
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.