ML

Llama-Guard-4-12B

Multimodalby Meta Llama·Model page

Meta's 12B-parameter Llama 4-based multimodal safety classifier for detecting policy violations in text and image inputs.

Max output

Most tokens the model can return in a single response.

16Ktokens
Share:
Author
ML
Meta Llama
Organization · ✓
meta-llama
Details
Downloads154.1K
Likes106
AccessOpen Source
Context164K tokens
Input price$0.18 /1M
Output price$0.18 /1M
Taskimage-text-to-text
Parameters12B
Licenseother
Librarytransformers
Knowledge cutoffAug 31, 2024
CreatedApr 23, 2025
UpdatedApr 29, 2025
View on Hugging Face
Languages
en
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Llama-Guard-4-12B — AI Model Details | Applied