Shieldstral is a 3B open-weights multimodal safety classifier under Apache 2.0 that matches or outperforms open guard models up to 7x its size on text safety, refusal detection, policy adaptability, and multimodal benchmarks. It runs on a single 16GB NVIDIA GPU.
Added to The Deploy Log , updated . Read Edition 46, the edition that carried it.
14 rows from Mistral in The Deploy Log are dated on or before this one, this one included.