Mistral出了个3B的小模型，能按你自定义的政策做内容审核，效果追平20B大模型，还只要16G显存，开源可商用。
Mistral AI推出开源权重模型Shieldstral 1.0 3B，将内容审核转化为单个是非题，用户可在推理时用自然语言指定政策，无需重新训练。该模型基于Ministral-3-3B-Base-2512和Pixtral视觉编码器，使用约54.1M样本训练。其在文本安全任务上平均F1为84.9%，与GPT-OSS-Safeguard-20B持平；多模态安全F1为83.8%，适应性基准达91.3%。模型仅需16GB显存，采用Apache 2.0许可证。
Mistral AI Releases Shieldstral 1.0 3B: An Open-Weights Policy-Adaptive Multimodal Safety Classifier Matching Models 7× Its Size
Mistral AI has released Shieldstral 1.0 3B, an open-weights, policy-adaptive multimodal safety classifier that frames content moderation as a single yes/no question instead of a fixed harm taxonomy. Operators supply the policy as a plain-language query at inference time and get back a calibrated safety score from one forward pass — no retraining required to re-target the model. Built on Ministral-3-3B-Base-2512 with a Pixtral vision encoder and trained on roughly 54.1M samples, it reports 84.9% average F1 on text safety (matching GPT-OSS-Safeguard-20B), 83.8% on multimodal safety, and 91.3% on Mistral's adaptability benchmark — while fitting in 16GB of VRAM under an Apache 2.0 license. The post Mistral AI Releases Shieldstral 1.0 3B: An Open-Weights Policy-Adaptive Multimodal Safety Classifier Matching Models 7× Its Size appeared first on MarkTechPost .