Self-hosted inference engine that runs large MoE models such as GLM-5.3-Flash on your own GPU, with OpenAI-compatible APIs.
2.6K+318 this week370CudaMITWell maintainedUpdated yesterday
1 alternative
Best open-source alternatives to llama.cpp (2026)
Looking for a free, open-source alternative to llama.cpp? These 1 projects can replace it. Each one passed our quality screening and is explained in plain words, so you can compare stars, license and maintenance at a glance.
Quick comparison
| Project | Stars | License | Last commit |
|---|---|---|---|
| mw00/project-maya | ★ 2.6K | MIT | yesterday |
FAQ
- Is there a free, open-source alternative to llama.cpp?
- Yes. The most popular open-source alternatives to llama.cpp on Repolode are project-maya.
- Which llama.cpp alternative should I choose?
- project-maya has the most GitHub stars and is released under MIT. Compare the license and last commit of each option in the table above before choosing.
How this list is made: AI reads each project's documentation to match it with products it can replace, every project passes our quality screening, and the list is ranked by GitHub stars. Stars updated Nov 6, 2026. How Repolode works