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

0.34.03w ago

ollama/ollama v0.34.0

Original

Key point

Ollama v0.34.0 is an update that includes support for ChatGPT Desktop integration, improved structured output performance on Apple Silicon, and enhanced OpenAI compatibility.

Details

Key Features

ChatGPT Desktop Integration: Ollama models can now be used directly in the ChatGPT desktop app. This can be configured via the Ollama app on MacOS, allowing you to run open models while maintaining existing workflows.
Improved OpenAI Compatibility: Supports tool search and response compaction features in OpenAI-compatible clients.

Performance Improvements

Apple Silicon Optimization: Structured output performance has been improved on devices with Apple Silicon chips.

Bug Fixes

Image Processing: Fixed an issue to ensure images are displayed correctly through compacted responses.

ollama releases | AI Briefing