Add Laguna M.1 GGUF support by empty-quiver · Pull Request #2003 · ikawrakow/ik_llama.cpp

Support for the Laguna M.1 model, with 225 billion parameters, has been added to the ik_llama.cpp repository, enabling practitioners to leverage this GGUF format model. This follows prior support for the Laguna XS.2 model, which has 33 billion parameters. The addition enhances the capabilities of the ik_llama.cpp framework, allowing AI engineers to experiment with larger models and optimize their applications using these advanced architectures.