Ollama has released a new app for macOS and Windows that simplifies interactions with models by allowing users to download and chat with them directly. The app enhances user experience by supporting file drag and drop, enabling easier interaction with text or PDFs, and allowing context length adjustments for processing large documents, although this may require additional memory. It includes multimodal support, permitting the input of images for compatible models like Google DeepMind’s Gemma 3. Additionally, the app offers features for processing code files to aid in documentation writing. Users can download the app for these operating systems, while pure CLI versions are also available on Ollama's GitHub releases page.