v0.30.0-rc17

v0.30.0-rc17 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 compatibility with GGUF file format, with MLX used to accelerate model inference on Apple Silicon. This release candidate was part of Ollama's pre-release testing phase to gather feedback on performance, stability, and memory utilization before the final v0.30.0 release.

Source: Ollama Releases | 2026-05-14