b9549

Release b9549 of llama.cpp adds support for the Gemma4 MTP model architecture . The release includes pre-built binaries for multiple platforms including macOS, Linux, Android, and Windows with various hardware accelerator options such as CUDA, ROCm, and Vulkan. This build follows the project's ongoing effort to expand model architecture support and maintain compatibility across different operating systems and hardware configurations.

Source: llama.cpp Releases | 2026-06-07