Project Maya
Run a 321B AI model on your GPUs
mw00Third-party software from public repositories. bestappfor.me does not host it, does not verify it and is not responsible for its use. Download only from the official source and check the license. Terms and disclaimer
About
Run the GLM-5.3-Flash language model, with 321 billion parameters, on your own graphics cards, from a single NVIDIA GPU up to 16. Chat in the browser, generate pictures, and connect coding tools through an API compatible with OpenAI and Anthropic. Nothing leaves your machine.
The engine is built for this one model. It keeps the most used experts on the GPU, others in RAM and the rest on an NVMe SSD, and moves them as you chat. It measures your hardware and tunes itself. AMD and Windows support are experimental.
Highlights
- Runs on one NVIDIA GPU or up to 16
- OpenAI- and Anthropic-compatible API
- Chat and live monitor in the browser
Who it's for
Good for people with several GPUs who want a large AI model that keeps data on their machine.
This description was written by our editors with automated assistance, not by the developer, and has not been reviewed yet.
Why it is here
- Created 7 days ago
- About 823 stars a week
- Code changed today
- New release today
