Ollama released version 0.16.0 yesterday, enhancing its local large language model ecosystem with new models and a simplified command-line interface. The update introduces GLM-5, a 744 billion parameter agentic model from Z.ai, built for complex systems engineering and long-horizon tasks. Also included is MiniMax-M2.5, a new state-of-the-art large language model designed for real-world productivity and coding. The release also features a new 'ollama' command, intended to simplify the process of launching applications with models. Additionally, improvements have been made to Ollama's MLX runner, adding support for the GLM-4.7-Flash model.