Multimodal open d1 decision models for the edge

Liquid AI has released two open decision models, d1-3B and d1-omni-600M, designed for fast, structured decisions on edge devices. The d1-3B model is a 3-billion parameter multimodal model supporting text and images, outperforming larger models on decision-making benchmarks. The smaller d1-omni-600M is an experimental model that can handle text, images, and audio. These models are optimized for speed, with d1-3B providing answers in milliseconds on NVIDIA Jetson hardware. Unlike generative models, they produce answers in a single forward pass for tasks like classification and quality assessment.