Built in C++, project-maya is an open-source LLM inference tool maintained by mw00. It has 1k GitHub stars and 136 forks, and was last updated in October 2026. Topics include cuda, glm and glm-5.
“Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.”
— mw00, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 1,032 |
| Forks | 136 |
| Language | C++ |
| License | MIT |
| Last updated | |
| Owner | mw00 |
| Website | huggingface.co/peasantsmith/GLM-5.3-Flash-Maya-GGUF |
| Repository | mw00/project-maya |
Tags
cudaglmglm-5llmllm-inferencelocal-llmmixture-of-expertsmoe
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.