project-maya
Lets anyone run a very large open-weight AI model privately on their own GPUs instead of relying on a cloud provider.
View mw00/project-maya on GitHub- GitHub stars
- 2,851
- Forks
- —
- Language
- C++
Project details
- Repository
- mw00/project-maya
- Licence
- MIT
- Primary language
- C++
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.
Explore by topic
More tools in Models & training
- llama-modchip
synchopate · Apache-2.0
Lets you run a huge 284-billion-parameter AI model on an ordinary 64GB computer using only the CPU, no GPU required.
- slotstream
carloslfu · MIT
Runs a 125-billion-parameter language model on a Mac with far less RAM than it needs by streaming parts of the model from the SSD.
- kimi-k3-in-c
fareedkhan-dev · Apache-2.0
Lets a 2.78-trillion-parameter AI model run inference on a regular laptop with no GPU and just 8GB of RAM, by rewriting the whole inference engine in dependency-free C.
- kaggle-tpu-lab
arahim3 · MIT
A recipe for serving the 27B-parameter Qwen3.8 model on Kaggle free TPUs with a public OpenAI-compatible endpoint and a 262k-token context window, no paid GPU.