Mistral Releases Shieldstral: A 3B Open-Source Content Safety Model

Mistral introduced Shieldstral, a 3-billion parameter open-source multimodal safety model. It achieves SOTA performance, outperforming much larger models while running efficiently on a single 16GB GPU and allowing for customizable enterprise safety standards.

2026-08-05 ~ 2026-08-05 · 3 related posts

• Mistral releases Shieldstral: 3B multimodal safety classifier runs on a single GPU — MistralAI · 2026-08-05
• Mistral releases Shieldstral, a 3B open-weights content safety model for on-device deployment — MistralAI · 2026-08-05
• Mistral details Shieldstral: SOTA multimodal moderation, runs on a single GPU — MistralAI · 2026-08-05