Ollama recently released version 0.32.8, introducing the Muse Glimmer model across all supported platforms. Muse Glimmer is designed to power local AI applications, including coding agents such as Claude Code, Codex, and Pi, as well as long-running personal assistants like OpenClaw and Hermes. The release leverages Ollama's MLX engine, which provides optimized performance for Muse Glimmer on Apple Silicon. This model also incorporates DFlash and image input capabilities, features that were integrated in Ollama 0.32.7. Users can run Muse Glimmer locally using the 'ollama run muse-glimmer' command, or integrate it with other tools like Claude Code by specifying the model during launch.