Ollama v0.30.0 Released with Improved llama.cpp Compatibility

Core summary

One sentence to understand this update

Ollama 0.30.0 has been released, featuring improved compatibility and performance through llama.cpp, extending support to a wider range of hardware beyond Apple Silicon's MLX engine.

Impact & opportunity

What this could mean

Developers can now deploy Ollama on more diverse hardware configurations with better performance, enabling broader local LLM experimentation.