Ollama v0.30.0 Redesigns Architecture for Direct llama.cpp Support and GGUF Compatibility

Core summary

One sentence to understand this update

Ollama v0.30.0 features a re-architected core to directly support llama.cpp instead of GGML, enabling GGUF file compatibility and MLX acceleration for Apple devices.

Impact & opportunity

What this could mean

This architectural shift in Ollama provides improved compatibility with the GGUF format and potentially better performance for local LLM inference, especially on Apple hardware.