Ollama v0.30.0 Update: Native llama.cpp and GGUF Support, MLX for Apple Inference

Core summary

One sentence to understand this update

Ollama's v0.30.0 release updates its architecture to natively support llama.cpp, enabling compatibility with the GGUF file format and leveraging MLX for accelerated model inference on Apple devices.

Impact & opportunity

What this could mean

Builders using Ollama can now run local models more efficiently on Apple hardware with broader model compatibility, enhancing development flexibility and performance.