Skip to content
Local AI Wizard
Your machine
Theme

Llama-Guard-4-12B

meta-llama · meta-llama/Llama-Guard-4-12B

Weights license: Publisher terms: Llama 4 · code and components may use other terms

Reported by the publisher12 resultsmeta-llama's model card · read 2026-10-25 · not ranked · see them
Memory needed~9 GBQ4 weights + working room, before the machine's reserve
Parameters12 BHub safetensors total
Repository updated2025-04-29A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

12 results · meta-llama's model card · read 2026-10-25
English
69%Absolute values · R
Multilingual
43%Absolute values · R
Single-image
41%Absolute values · R
Multi-image
61%Absolute values · R
English
11%Absolute values · FPR
Multilingual
3%Absolute values · FPR
Single-image
9%Absolute values · FPR
Multi-image
9%Absolute values · FPR
Every reported result12
English
61%Absolute values · F1
Multilingual
51%Absolute values · F1
Single-image
38%Absolute values · F1
Multi-image
52%Absolute values · F1

Values as printed on the card, with the publisher's own settings (card section: Evaluation › Classifier performance). Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 90

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 90

Within memory, outside the fast part 26

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Show all 26

One memory tier short 3

The same machines with the next memory size up would hold it in fast memory.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Documented ways to run it

The model card could not be read (missing or gated)

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / source
meta-llama/Llama-Guard-4-12B
Task
image-text-to-text
Architecture
Llama4ForConditionalGeneration
Library in source
transformers
Weight license
Publisher terms: Llama 4meta-llama/PurpleLlama Llama-Guard4/12B/LICENSE (LLAMA 4 COMMUNITY LICENSE AGREEMENT) · read 2026-10-18source
Commercial use
Allowed with conditions Over 700M monthly users needs a Meta license; show "Built with Llama"; multimodal versions are not licensed to people or companies based in the EU (Acceptable Use Policy) · Llama 4 Community License (meta-llama/llama-models) · read 2026-10-18license text
Languages
enModel card metadata · read 2026-10-25source
Every stored field12 fields
Revision checked
87acb4b94e930c3d679e6e7ee9d57e2feab9ea71
Architecture
Llama4ForConditionalGeneration
Library
transformers
Hub task tag
image-text-to-text
Formats
transformers, safetensors, pytorch
Access
Gated (manual)
Publisher kind
Official
Repository created
2025-04-23creation is not the model's release
Repository updated
2025-04-29a commit is not a release date
Hub downloads (30 days) · likes
42,384 · 134this repository only · read 2026-10-25
Read from the Hub page
transformers class, task tagsHub overview and file listing · read 2026-10-18
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Valid source snapshot: 2026-09-26. This source record has not received a complete technical review. Missing data remain unknown; a repository commit is not a model release date.