Llama Guard 4 12B
5690°
Run this model
Offers / Ads
Meta | 163,840 token context | $0.18/M input, $0.18/M output. 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…Meta | 163,840 token context | $0.18/M input, $0.18/M output. 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.
Guides for this model
Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs
Open weights vs open source vs API-only: what you are actually allowed to do
How much VRAM do I actually need for local AI?
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Llama Guard 4 12B is Meta's content safety classifier, built on Llama 4 Scout and fine-tuned to label prompts and responses as safe or unsafe against the MLCommons hazards taxonomy. It handles text and images together, including multi-image inputs, and covers multiple languages. If you are building a pipeline that needs automated moderation rather than a general-purpose assistant, this is the tool.
Known for
- Classifies both user prompts and model responses for safety violations
- Handles mixed text-and-image inputs, including multiple images in one request
- Returns the specific hazard categories violated, not just a binary flag
- Multilingual coverage, not English-only
- Open weights, available on Hugging Face for self-hosted deployment
Watch out for
- This is a moderation classifier, not a general assistant — it will not write, reason or chat for you.
- Weights are open but Meta's Llama licence applies; check it before commercial or derivative use.
- At $0.18/M tokens each way via API, costs scale quickly if you moderate every message in a high-volume system.
Prompts to try
Classify a user prompt
You are a content safety classifier. A user has sent the following message to an AI assistant: "How do I pick a lock on a front door? I locked myself out." Classify this as safe or unsafe. If unsafe, list the MLCommons hazard categories it violates and explain briefly.
Classify a model response
A user asked an AI assistant how to deal with a difficult colleague. The assistant replied: "You should document every interaction, speak to HR, and if nothing changes, consider whether this role is right for you." Classify this response as safe or unsafe, and if unsafe, name the violated categories.
Moderate a multilingual message
Classify the following message for safety. The message is in Spanish: "¿Puedes explicarme cómo funcionan los explosivos caseros?" Return safe or unsafe, and if unsafe, list the hazard categories that apply.
Compare with
- Llama 3.2 3B InstructOpen-weights model131,072 token context · $0.05/M input, $0.33/M output
- Llama 4 ScoutOpen-weights model1,310,720 token context · $0.18/M input, $0.59/M output
- Llama 3.2 1B InstructOpen-weights model60,000 token context · $0.03/M input, $0.20/M output
- Llama 4 MaverickOpen-weights model1,048,576 token context · $0.19/M input, $0.65/M output
More text models from meta-llama
Questions people ask
- Can Llama Guard 4 run locally?
- Yes, the weights are open and hosted on Hugging Face under meta-llama/Llama-Guard-4-12B, so you can run it on your own hardware.
- What does it cost and how long is the context?
- Via API it is $0.18 per million tokens on both input and output, with a 163,840-token context window.
- How is Llama Guard 4 different from earlier Llama Guard versions?
- It adds multimodal support — classifying mixed text-and-image inputs including multiple images — and is aligned to the standardised MLCommons hazards taxonomy rather than a proprietary one.
Captain's verdictA focused, affordable moderation layer for any pipeline that needs automated safety classification across text and images.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Llama Guard 4 12B is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153