llama-guard-3-8b
meta
Loading...
Loading...
Run side-by-side checks for pricing, context window, and latency.
ilsp
Open-source CoRM model from ilsp — available for download and self-hosting on Hugging Face.
dr-housemd
Open-source GLM-4.7-Flash-exl3-3bpw-H4 model from dr-housemd — available for download and self-hosting on Hugging Face.
redhatai
Open-source gpt-oss-120b-essential model from redhatai — available for download and self-hosting on Hugging Face.
meta
Let our experts help you evaluate models based on your actual use case and budget. We'll provide a free analysis and actionable recommendations.
Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.