Mistral releases Shieldstral, a 3B open-weights content safety model for on-device deployment

MistralAI · x · 2026-08-05

Mistral introduces Shieldstral, a 3B open-weights model for content safety that can be deployed on-device. It achieves state-of-the-art multimodal moderation with industry-leading efficiency, running on a single 16GB NVIDIA GPU, and gives enterprises customized control over safety standards.

Related event: Mistral Releases Shieldstral: A 3B Open-Source Content Safety Model(3 posts)→

Original post →

More from Models

Models channel →