v0.30.0-rc22

v0.30.0-rc22 is a pre-release version of Ollama that changes the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on Apple Silicon. Known issues in this pre-release include that laguna-xs.2 and llama3.2-vision are not yet supported.

Source: Ollama Releases | 2026-05-21