Ollama v0.30.8 Released with Prompt Caching and MLX Inference Improvements

Core summary

One sentence to understand this update

Ollama's v0.30.8 update introduces improved prompt caching for better KV cache reuse and more stable MLX inference, alongside other bug fixes.

Impact & opportunity

What this could mean

Builders can expect more efficient model execution and improved stability when using Ollama for local LLM deployment and experimentation.