guard
Llama Prompt Guard 2 86M
Meta prompt injection and jailbreak detection model (mDeBERTa base unverified; card not read).

Levelmodel
Classguard
Parameters86M
Contextnot in the notes
ReleasedApr 2025
Opennessopen weights restricted
Runs onnot in the notes
Statusactive
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- not in the notes
- Total parameters
- 86M sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights restricted
- Licence
- Llama 4 Community License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- Multilingual (unverified)
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
Developer
Metabig tech, USA
Metabig tech, USAModel
Llama Prompt Guard 2 86MMeta, guard
Llama Prompt Guard 2 86MMeta, guardR&D TopicsGuardrails and Safety Classifiers
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 1
Sources
- huggingface.co/meta-llama https://huggingface.co/meta-llama
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Llama Prompt Guard 2 86M", https://aurion.semai.id/models/meta-llama-prompt-guard-2-86m/, records of October 2026.