Ollama App Release for macOS and Windows

Ollama has launched a new application for macOS and Windows that provides a built-in graphical user interface (GUI) for downloading and chatting with local AI models. This update transforms Ollama from a primarily CLI-driven tool into a more accessible platform for users to interact with large language models (LLMs) locally.

Integrated Chat Interface

Ollama's new app provides a direct way to download and chat with models without needing external interfaces or third-party front-ends. This integration simplifies the onboarding process for users on macOS and Windows, allowing them to manage models and initiate conversations within a single application.

File Processing and Context Management

The application supports drag-and-drop functionality for files, enabling users to reason with text files and PDFs. To handle larger documents, the app includes a settings menu where users can increase the context length. Increasing the context length allows the models to process more information from a document, though it requires more system memory.

Multimodal Capabilities

Leveraging Ollama's multimodal engine, the new app allows users to send images to models that support multimodal inputs, such as Google DeepMind's Gemma 3 model. This enables the app to perform visual reasoning and image analysis locally.

Code Understanding and Documentation

The app is designed to handle code files, which models can process to help users understand complex codebases or generate documentation. By uploading code files directly into the chat, users can leverage local LLMs for technical analysis and documentation writing.

Availability and Installation

The는 new app is available for download on macOS and Windows. For users who prefer a command-line interface, standalone CLI versions of Ollama remain available via the project's GitHub releases page.