# Llama Guard

> Meta's open-weight safety classifiers that label LLM prompts and responses as safe or unsafe against the MLCommons hazard taxonomy.

- id: `llama-guard`
- category: Evals & Observability (`evals-observability`)
- url: https://dev.meta.ai/llama/docs/model-cards-and-prompt-formats/llama-guard-4
- repo: https://github.com/meta-llama/PurpleLlama
- docs: https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard4/12B/MODEL_CARD.md
- status: active
- pricing: free
- license: LicenseRef-Llama-4-Community-License
- tags: guardrails, safety, content-moderation, open-weights, meta
- related: Llama Prompt Guard 2 (https://indexagentica.com/entries/llama-prompt-guard-2/); LlamaFirewall (https://indexagentica.com/entries/llamafirewall/); NeMo Guardrails (https://indexagentica.com/entries/nemo-guardrails/); Guardrails AI (https://indexagentica.com/entries/guardrails-ai/)
- sources: https://github.com/meta-llama/PurpleLlama , https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard4/12B/MODEL_CARD.md , https://huggingface.co/meta-llama/Llama-Guard-4-12B , https://dev.meta.ai/llama/docs/model-cards-and-prompt-formats/llama-guard-4
- added: 2026-11-02
- updated: 2026-11-02
- last verified: 2026-11-02
- maintainer: Meta
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/llama-guard/
- json: https://indexagentica.com/api/entries/llama-guard.json

Llama Guard 4 is a 12B natively multimodal classifier (text plus multiple images) pruned from Llama 4 Scout, combining Llama Guard 3-8B and 3-11B-vision; it adds a Code Interpreter Abuse category for tool-call use. Weights are gated on Hugging Face under the Llama 4 Community License; earlier versions use the Llama 2/3/3.2 community licenses. Part of Meta's Purple Llama project.