Llama Guard 4 12B
Meta AI's Llama Guard 4 12B is a multimodal safety classifier and chat model with 12 billion parameters, capable of processing up to 163,840 tokens and handling text and image inputs. It excels at content safety classification, supporting both text-only and mixed text-and-image prompts, and can generate text outputs indicating safety or hazards.
Input
Output
Context
1049K
Max Output
8K
Parameters
12B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Resources & Links
Estimated GPU requirements for Llama Guard 4 12B
Estimates based on INT8 quantization at up to 32K context. A count above one assumes tensor parallelism across the cards. Actual requirements vary by framework and configuration.
More models by Meta AI
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Llama Guard 4 12B
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Llama Guard 4 12B advertises a context window of 1,048,576 tokens, with a maximum output of 8,192 tokens in a single response. The figure is the creator's published maximum; a given host may serve less, and the gateway routes on what each host actually serves.
Yes. Llama Guard 4 12B is an open-weight model released under the Other license, so the weights can be downloaded and self-hosted within that license's terms.
Llama Guard 4 12B accepts Text and Image and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
No published benchmark result for Llama Guard 4 12B is in the catalog yet, so the model is shown as unmeasured. It is not ranked or estimated; the router treats it as unknown for every task until a suite measures it.
Yes. Llama Guard 4 12B is served on the managed pool through the OpenAI-compatible endpoint as meta-llama/Llama-Guard-4-12B, pinned by name or chosen by routing when it is the best fit for a request. The Try in Playground button opens it directly.
About 12.1 GB at INT8 for the weights and a default context, from the catalog's 12B parameter count; FP16 needs roughly twice that, and long contexts or many concurrent requests add KV cache on top. The GPU section on this page lists cards that hold it, and the capacity planner sizes it for your context length and traffic.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Sep 13, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.