Ollama v0.30.0 Update: Direct llama.cpp Support, GGUF Compatibility, MLX Acceleration

Core summary

One sentence to understand this update

Ollama's v0.30.0 release shifts its architecture to directly support llama.cpp instead of GGML, adds GGUF file format compatibility, and uses MLX for accelerated model inference on Apple devices.

Impact & opportunity

What this could mean

Developers will benefit from Ollama's more native llama.cpp integration, GGUF compatibility, and MLX-powered performance boosts on Apple devices, simplifying local LLM deployment.