Llama Prompt Guard 2
MetaMeta's compact prompt-injection and jailbreak classifier (86M and 22M), labeling prompts benign or malicious. Part of LlamaFirewall, it is tuned for very low latency (sub-100ms) and high precision, with multilingual coverage across eight languages.
Llama Prompt Guard 2 comes in two sizes, 86M and 22M, the smaller trading a little recall for roughly a quarter of the latency. The card publishes no training data. The weights are behind Meta's access request rather than open to download. Verified 2026-08-13 via the HF model card.
Openness
3 medium confidence- weights
- open(Llama-Prompt-Guard-2-86M/22M on HF)
- data
- not-released
- license
- Llama-4-Community(NOT OSI)
Open weights under Meta's Llama 4 Community License, which is use-restricted and not OSI-approved, so open_weights (3) like the rest of the Llama family.
- https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-86M recorded 2026-08-13
Repo shows License - llama4 and carries the full LLAMA 4 COMMUNITY LICENSE AGREEMENT text, including the 700 million monthly active user threshold above which a separate Meta license is required. Gated manual, with model.safetensors downloadable on acceptance. The card publishes no training set and declares no datasets.
- https://huggingface.co/api/models/meta-llama/Llama-Prompt-Guard-2-86M recorded 2026-08-13
cardData records license - other with license_name - llama4; gated - manual; siblings list model.safetensors; no datasets key.
Adoption
3 high confidence111,334 downloads in the trailing 30 days for the one declared artifact, meta-llama/Llama-Prompt-Guard-2-86M, which bands at 100K-1M, level 3 on the software and model adoption scale.
- https://huggingface.co/api/models/meta-llama/Llama-Prompt-Guard-2-86M recorded 2026-08-13
111,334 downloads in the trailing 30 days for meta-llama/Llama-Prompt-Guard-2-86M
Capability
4 medium confidenceSpecialized injection/jailbreak classifier with strong accuracy and very low latency; complements full-taxonomy guards.
- https://huggingface.co/meta-llama/Llama-Prompt-Guard-2-86M recorded 2026-08-13
Card evaluation table gives Llama Prompt Guard 2 86M an English AUC of .998, recall at 1% FPR of 97.5%, multilingual AUC .995 and 92.4 ms per classification on an A100; the 22M variant is listed at .995/88.7% and 19.3 ms. Repo is tagged 8 languages, and the card frames the task as prompt injection and jailbreak detection.
Verified 2026-08-13