v0.30.0-rc16

v0.30.0-rc16 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. This release candidate includes bug fixes and refinements as part of the v0.30.0 development cycle.

Source: Ollama Releases | 2026-05-14