Ollama v0.14.1 was released today, January 18, 2026, bringing experimental support for image generation models. This new functionality is available for Linux systems configured with CUDA-compatible GPUs, in addition to macOS. The initial model provided is Z-Image-Turbo, which can be executed via the command "ollama run x/z-image-turbo." As noted in the release, the "x" prefix on ollama.com denotes experimental models. Ollama plans to expand this offering with additional models, including Qwen-Image-2512, Qwen-Image-Edit-2511, and GLM-Image, in subsequent updates. This update broadens Ollama's local AI capabilities to include image synthesis for supported Linux environments.