llamafile allows AI developers to distribute and run LLMs with a single file. It supports multiple CPU microarchitectures and CPU architectures, as well as six operating systems. The weights for LLMs can be embedded within the llamafile for easier distribution.

9m read timeFrom github.com
Post cover image
Table of contents
Binary InstructionsSource Instructionszipalign documentationTechnical DetailsLicensingKnown Issues

Sort: