mw00 / project-maya
Run 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.
Why this job: topics: local-llm, llm-inference, gguf, quantization
What it does
Models this size usually need a datacenter. Maya runs three of them on the hardware you already have:
Get started
git clone https://github.com/mw00/project-maya.git && cd project-maya
./setup.sh - Maintenance
- Active
- Last commit 2 days ago
- Stars
- 2,712
- +269 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.1.57
- Released today
- Built with
- C++
- 36% of the code
Is it looked after?
- Contributors
- 15
- Last 90 days
- Issues
- 80% closed
- 81 still open
- Pull requests
- 179 merged
- 58 waiting
- Releases
- 93
- 30+ in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Indras-Mirror / Xolotl | 490 | today | MIT | No downloads |
| simplexai-labs / PolyStrata | 938 | 2 days ago | MIT | Windows |
| Yamz-Labs / kyojin | 233 | today | MIT | No downloads |
More: languages, topics and project record
Languages
- C++ 36%
- Cuda 35%
- Python 24%
- JavaScript 2%
Topics
- cuda
- glm
- glm-5
- llm
- llm-inference
- local-llm
- mixture-of-experts
- moe
- openai-api
- quantization
- rocm
- self-hosted
Project record
- JobLocal LLMs
- StatusFeatured
- Commits1,075
- Forks386
- Watching16
- Stars in 28 days+2,050
- CreatedOct 6, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026