Local Ai
b9503
Release b9503 of llama.cpp fixes multimodal (mtmd) support by handling Gemma 4 audio projector embedding size , specifically removing the projection_dim from clip_n_mmproj_embd. This build includes pr
Release b9503 of llama.cpp fixes multimodal (mtmd) support by handling Gemma 4 audio projector embedding size , specifically removing the projection_dim from clip_n_mmproj_embd. This build includes pre-compiled binaries for multiple platforms including macOS, Linux, Android, and Windows with various hardware acceleration backends (CPU, Vulkan, ROCm, CUDA, OpenVINO).
Source: llama.cpp Releases | 2026-06-04