Liquid AI releases d1-3B, a 3B multimodal decision model for edge deployment
LiquidAI/d1-3B
AISummary
Liquid AI has released d1-3B, a 3B parameter multimodal model post-trained to return calibrated, typed answers to yes/no, choice, and score questions in one forward pass. The source reports a Decision Index 0.2.1 score of 48.57, the highest among models under 10B in its table, and 8 ms per decision on an NVIDIA RTX 4090.
AIWhy it matters
The source gives benchmark scores against named peer models and edge latency figures across several hardware targets, helping readers judge fit for on-device decision pipelines.
Source: Liquid AI · new models on Hugging Face · huggingface.co