AllFeed, trending, and board
FeedLatest news
TrendingOpen source and releases
BoardBlogs and showcases
TagsBrowse by topic

AI Briefing

Privacy Policy Terms of Service Contact About Sources RSS Support us

Home
Trending
Tags
Settings

ollama releases | AI Briefing

Back to releases

ollama

ollama/ollama

Ollama: Local Open Model Runnerready

Ollama is a tool that provides a CLI and REST API for running and managing open models locally. It is installed and used on macOS, Windows, Linux, and Docker environments, primarily utilized by developers and teams building AI application and agent integrations. Releases are important as they directly impact installation methods, CLI/API compatibility, the model execution experience, and official integrations and platform support.

ailocal-llmcliapiopen-source

Choose version

0.40.165d ago

ollama/ollama v0.40.16

Key point

Adds Ripple Preview model and improves Apple Silicon memory efficiency, including API behavior fixes

Details

Key Features

Ripple Preview (Ricursive Intelligence) 65B dense model added: A model optimized for agentic coding, runnable via the ollama run ripple-preview command
CUDA 13.5 support added: Available in Windows on ARM environments

Performance Improvements

Qwen3.8 Flash Next: Reduced memory usage by approximately 27 GiB on Apple Silicon

Bug Fixes and API Changes

/v1/responses: Now respects the truncation parameter and no longer truncates implicitly by default
/v1/models: Fixed to return an empty list instead of null when a model is not installed
ollama launch claude: Fixed to always route to Claude Code with the selected model
ollama launch: Improved to explain the fact when a cloud model is deprecated