A smaller version of the Inkling AI model has been released by Thinking Machines Lab. The new model, called Inkling-Small, has a significantly reduced size compared to its predecessor, while maintaining similar performance. Inkling-Small can run on a single NVIDIA B300 GPU, making it more accessible to researchers and developers. The model's multimodal capabilities and open weights architecture make it a valuable tool for various AI applications. The release of Inkling-Small is notable because it offers a more efficient and accessible alternative to the original Inkling model, potentially expanding its use in AI research and development.