llama-guard-4-12b

Name: llama-guard-4-12b
Author: NVIDIA

moderationllama412B

Capabilities

Show unsupported (5)

Reasoning & Interaction

Tool Calling

Infrastructure

Streaming

Fine-tuning

ProviderNVIDIA

Licensellama4

Status—

Typemoderation

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters12B

Architecture—

Context window—

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date2025-04-23

Sourceofficial

GET/v1/models/nvidia/meta/llama-guard-4-12b

Changes · 4 entries

meta/llama-guard-4-12bupdateb301ebeMar 23, 2026, 11:47 PM

modalitiesinput["text"]output["text"]

meta/llama-guard-4-12bupdate2b100acMar 23, 2026, 05:30 AM

parameters12

meta/llama-guard-4-12bupdateb50649fMar 21, 2026, 11:58 PM

model_typemoderation

meta/llama-guard-4-12bcreate7f5c66fMar 21, 2026, 05:16 AM