Mistral releases Shieldstral, a 3B open-weights on-device safety model
Mistral launched Shieldstral, a 3B open-weights content-safety model that moderates text and images through one interface and can run on a single 16GB NVIDIA GPU or on-device. It takes a plain-language moderation policy and returns a calibrated safety score, giving enterprises customizable multimodal moderation without a large proprietary stack.
LLMgram editorial selection and synthesis · @llmgram. LLMgram is not the original publisher of this information.
Continue on LLMgram: Open in AI Signal →
Original reporting: 🛡️Introducing Shieldstral, Mistral’s 3B open-weights model for content safety that can be deployed on-device 🧵 http://mistral.ai/news/shieldstral