UTC

Llama Guard 4 12B

Meta · open weights · served by 6 providers · image input

meta/llama-guard-4-12b

Weights
Open
Released
2025-04-29
Knowledge cutoff
Not stated
Context window
164K
Hugging Face repository

meta-llama/Llama-Guard-4-12B at commit 87acb4b94e, last changed 2025-04-29

Licence
llama4
Access
Gated (approval)
Library
transformers
Formats
.safetensors
  • No model signature file is published with the weights.

What the Hub's scanners report

5 weight files, 5 with a scan result. No scanner reports an issue with them.

The model at this commit, its 5 weight files. The Hub shows file hashes of a gated model only after you accept its licence.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • Deep Inframeta-llama/Llama-Guard-4-12B
  • Eden AIdeepinfra/meta-llama/Llama-Guard-4-12B
  • Hugging Facemeta-llama/Llama-Guard-4-12B
  • Kilo Gatewaymeta-llama/llama-guard-4-12b
  • Nvidiameta/llama-guard-4-12b
  • OpenRoutermeta-llama/llama-guard-4-12b
Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.