Local AI & LLMsEditorially verified
RamaLama
containers/ramalama
Run local AI models through container tooling that detects available accelerators.
A developer utility for pulling and serving AI models through container-based runtimes. The README documents macOS and Fedora installation and accelerated container images selected for detected hardware; model choice and host configuration determine hardware needs.
GitHub stars
3,102
Forks
386
Open issues
116
Primary language
Python
Repository details
- License
- MIT LicenseMIT
- Default branch
- main
- Last commit
- Nov 2, 2026
- Repository updated
- Nov 3, 2026
- Last metadata check
- 2026-11-03
- Setup difficulty
- intermediate
- Self-hosting
- Self-hostable
- GPU
- Not documented
- API key
- Not required
- Paid service
- Not required for documented default
Categories & platforms
Local AI & LLMsDeveloper UtilitiesSelf-hosted Apps
Supported platforms
Linux · macOS · Containers
Topics
containerslocal inferenceGPU accelerationPython
Editorial notes
Public, active and unarchived. GitHub reports MIT. README confirms local container execution and accelerator-aware images; host and model requirements vary.
View license on GitHub