ollama v0.40.16

## Ripple Preview [Ripple Preview](https://ollama.com/library/ripple-preview) from Ricursive Intelligence is a 65B dense model built for agentic coding. ## What's Changed - Qwen3.8 Flash Next uses about 27 GiB less memory on Apple silicon - always routes Claude Code to the selected model - explains when a cloud model has been retired - respects and no longer silently truncates by default - returns an empty list instead of when no models are installed - CUDA 13.5 support for Windows on ARM - Updated llama.cpp **Full Changelog**: https://github.com/ollama/ollama/compare/v0.40.15...v0.40.16