Ollama v0.40.16 Released with Ripple Preview Support
#Ollama #Anthropic #Meta #NVIDIA
Ollama v0.40.16 has been released. It adds support for Ripple Preview, a 65B dense model for agentic coding, and includes changes such as reduced memory usage for Qwen3.8 Flash Next.
Ollama v0.40.16 has been released. It supports Ripple Preview, a 65B dense model built for agentic coding by Ricursive Intelligence. Additionally, Qwen3.8 Flash Next now uses approximately 27 GiB less memory on Apple silicon.
Other changes include a feature where Claude Code always routes to the selected model and an explanation provided when a cloud model has been retired. Regarding the API, /v1/responses now respects truncation and no longer silently truncates by default, and /v1/models returns an empty list instead of null when no models are installed. The update also includes CUDA 13.5 support for Windows on ARM and an updated llama.cpp.
This item is a summary. The full, checkable version is at the original source:
Read the original at Ollama ↗