Ollama v0.30.0 Shifts to llama.cpp Architecture and MLX Acceleration

Core summary

One sentence to understand this update

Ollama v0.30.0 redesigns its architecture to directly support llama.cpp, enabling GGUF file format compatibility, and utilizing MLX for Apple inference acceleration.

Impact & opportunity

What this could mean

This architectural shift in Ollama provides developers with better compatibility with the llama.cpp ecosystem, GGUF models, and optimized performance on Apple hardware via MLX.