Ollama v0.30.0 Integrates llama.cpp Directly, Adds GGUF Support & MLX Acceleration

Core summary

One sentence to understand this update

Ollama v0.30.0 revamps its architecture to directly support llama.cpp, enables GGUF file format compatibility, and uses MLX for accelerated inference on Apple hardware.

Impact & opportunity

What this could mean

Builders gain improved performance and broader model compatibility within Ollama, particularly benefiting Apple users with MLX acceleration.