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

0.34.31w ago

ollama/ollama v0.34.3

Original

Key point

Ollama v0.34.3 introduces per-model thinking control options, adds support for the Nemotron H vision model on Apple Silicon, and fixes bugs related to the macOS app and HuggingFace pulls.

Details

Key Changes

Feature Improvements

The GET /api/show endpoint now exposes the model's thinking control options and default values.
- You can check the supported thinking levels (e.g., false, true or low, high, max) and default values for each model via the CLI (ollama show) and the API.
- The same information is provided for cloud models on ollama.com.
Support for the Nemotron H vision model has been added in Apple Silicon (MLX) environments.

Bug Fixes

Fixed an issue where the macOS app would reopen windows that the user had previously closed when the app was activated.
Resolved issues that occurred when pulling models from HuggingFace.

ollama releases | AI Briefing