Meta: Llama Guard 4 12B

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs…

meta-llama/llama-guard-4-12b

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.

Llama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.

Specifications & capabilities

Input
image, text
Output
text
Context window · tokens
163840
Knowledge cutoff
2024-08-31
Published model ID
Llama-Guard-4-12B
Capabilities
multimodal, visionInput
Description source ↗

Published prices

1–4 / 4

Provider specifications & access

1–2 / 2

llama-guard-4-12b ↗

source model id
meta/llama-guard-4-12b
hosting
nvidia-catalog
platforms
  • NVIDIA Build / NIM
context length
163840
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    Llama-Guard-4-12B ↗

    source model id
    publishers/meta/models/llama-guard@llama-guard-4-12b
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • image
    • text
    output_modalities
    • text
    capabilities
    • multimodal
    • visionInput

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    31 / 100

    source id
    stanfordFMTI
    canonical model id
    meta-llama/llama-guard-4-12b
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    Meta
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    31 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Source specification observations

    1–4 / 4

    nvidiaNim ↗

    field
    context_length
    value
    163840
    normalized value
    163840
    scope
    source-model
    source id
    nvidiaNim
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    163840
    normalized value
    163840
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2024-08-31
    normalized value
    2024-08-31
    precision
    day
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    16384
    normalized value
    16384
    scope
    source-model
    source id
    openRouter
    confidence
    1

    Original sources

    1–12 / 12

    Hugging Face · meta-llama/Llama-Guard-4-12B ↗

    DeepInfra · Model page ↗

    Google Cloud · Model page ↗

    NVIDIA · Model page ↗

    OpenRouter · Model page ↗

    Google Cloud · Model documentation ↗

    NVIDIA · Documentation ↗

    DeepInfra · Catalog ↗

    GitHub · Catalog ↗

    Google Cloud · Catalog ↗

    NVIDIA · Catalog ↗

    OpenRouter · Catalog ↗

    Source links

    1–6 / 6

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace