Ollama adds Ricursive Intelligence's Ripple Preview coding model

Ollama released version 0.40.16, which brings Ripple Preview from Ricursive Intelligence into its model library. Ripple Preview is a 65B dense model built for agentic coding, and Ollama users can pull and run it with the command `ollama run ripple-preview`. The same release cuts memory use for Qwen3.8 Flash Next on Apple silicon by about 27 GiB, makes `ollama launch claude` always route Claude Code to the selected model, and has `ollama launch` explain when a cloud model has been retired. The `/v1/responses` endpoint now respects the truncation setting instead of truncating silently, `/v1/models` returns an empty list rather than null when nothing is installed, and CUDA 13.5 is supported on Windows on ARM. The bundled llama.cpp is updated too.