Ripple Preview v0.40.16 发布

v0.40.16

要点速览

Ripple Preview 是一个 65B 的密集模型，专为智能编码设计。Ricursive Intelligence 发布了 v0.40.16 版本，同时 Qwen3.8 Flash Next 在苹果硅芯片上减少了约 27 GiB 的内存使用。Claude 总是路由到选定的模型，且 /v1/responses 支持截断，不再默认静默截断。

正文

Ripple Preview

Ripple Preview from Ricursive Intelligence is a 65B dense model built for agentic coding.

ollama run ripple-preview

What's Changed

Qwen3.8 Flash Next uses about 27 GiB less memory on Apple silicon
ollama launch claude always routes Claude Code to the selected model
ollama launch explains when a cloud model has been retired
/v1/responses respects truncation and no longer silently truncates by default
/v1/models returns an empty list instead of null when no models are installed
CUDA 13.5 support for Windows on ARM
Updated llama.cpp

Full Changelog: v0.40.15...v0.40.16