What it does
MLC LLM is an engine that takes AI language models and converts them so they run well on many kinds of devices. That includes computers with different graphics cards, Macs, iPhones and iPads, Android phones, and even web browsers.
Its makers' goal is to let everyone run AI models on their own devices. Apps can talk to the models in the same way they'd talk to OpenAI's service, which makes switching easier.
Who it's for
Developers who want to put AI models inside apps on phones, computers or websites.
Can I use it without coding?
Developers only. It's a developer tool. Setup is explained in the online documentation. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Windows, Linux, Web browser, Phone
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- MLC-LLM: GPT/Llama on consumer-class GPUs and phonesHacker News · Apr 2023
- TensorIR: An Abstraction for Automatic Tensorized Program OptimizationResearch paper · Jan 2023
- Tensor Program Optimization with Probabilistic ProgramsResearch paper · Jan 2022
- TVM: An Automated End-to-End Optimizing Compiler for Deep LearningResearch paper · Jan 2018