Liquid AI Releases Open-Weight d1-3B and d1-omni-600M: Multimodal Decision Models With Zero Output Tokens

Liquid AI has launched two open-weight multimodal decision models, d1-3B and d1-omni-600M, designed for real-time decision-making without generating text output. These models process text with images or audio and provide calibrated probabilistic answers in a single pass, optimized for NVIDIA hardware.