Get an audit

Head to head · Guard self host · October 2026 research run

Llama Guard 4 vs Presidio

Presidio scores 66 (B) on agent readiness against Llama Guard 4's 49.1 (D), and leads in 6 of 7 scored categories. Both do guard self host.

Llama Guard 4Meta · Model API D49.1/100#533 of 629 PresidioData Privacy Stack · SDK + MCP B66/100#228 of 629

Which one, for what

Llama Guard 4 D

Good for A team outside the EU with a GPU that wants content moderation of text and images on its own hardware, against a fixed 14-category policy it can edit in the prompt.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Weights last changed on 29 April 2025, with no changelog, version tags or stated deprecation policy

Presidio B

Good for Detecting and masking personal data in prompts, outputs, logs and images on the owner's own machines, with detection tuned by entity, threshold and custom recognisers.

Ahead on

  • Reliability, 78 against 38
  • Schema & documentation, 69 against 52
  • Payments & pricing, 60 against 45
  • Maintenance & community, 63 against 28
  • Transparency & trust, 65 against 55

Also in its favour

  • Open source

Watch for

The REST containers have no authentication by design. The FAQ says to put a gateway or proxy in front

Score by category

CategoryWeight this runLlama Guard 4PresidioEdge
Reliability16%203878Presidio +40
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25269Presidio +17
Agent ergonomics13%16.26769Presidio +2
Security & auth14%17.55353even
Payments & pricing10%12.54560Presidio +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.82863Presidio +35
Transparency & trust7%8.85565Presidio +10
Negative events≤1500
Total49.1 · D66 · B

Facts side by side

FactLlama Guard 4Presidio
KindModel APISDK + MCP
VendorMetaData Privacy Stack
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP
AuthNoneNone
PricingFreeFree
x402nono
LicenceLlama 4 Community Licence (source-available weights, not an OSI licence), with the Llama 4 acceptable use policyMIT
Read-only variant documentednono
llms.txtnono
Last release2025-04-292026-07-22
Terms last updated2025-04-05no document linked
Privacy policy last updatedno document linkedno document linked
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity4.4k stars11k stars, 1.2M PyPI/wk

Verdicts

Llama Guard 4

A single self-hosted model classifies text and multi-image prompts against 14 MLCommons-aligned hazard categories and answers in a few tokens. The weights have not changed since 29 April 2025, download access needs Meta's manual approval, and the licence withholds the grant from individuals and companies based in the European Union.

Presidio

MIT-licensed personal data detector with a public OpenAPI document, tests on Python 3.10 to 3.14 and about 1.2 million weekly PyPI downloads. The REST containers have no authentication, the project states no SLA or support, and it covers personal data only, with no prompt injection or content moderation checks.

Before you call either

Llama Guard 4

  1. Request access on the Hugging Face page before anything else. Approval is manual, and the form cannot be edited after submission
  2. Send only the user turn to check an input, and the user turn plus the model's answer to check an output. The template picks the role from the message count
  3. Parse the first line for safe or unsafe and the second for category codes. Set max_new_tokens to about 10 and turn sampling off
  4. Do not send an image with no text. Meta says the model is not an image-only classifier, and S14 is skipped when an image is present
  5. Pair it with a prompt-attack detector. The card says the model can itself be moved by adversarial or injected text

Presidio

  1. Install from PyPI or pull images from ghcr.io/data-privacy-stack. The mcr.microsoft.com/presidio-* images are no longer updated
  2. Download a spaCy model (python -m spacy download en_core_web_lg) before the first AnalyzerEngine() call, or use the Docker image
  3. Send both text and language to /analyze. A request missing either returns HTTP 500 with a JSON error field
  4. Pass entities and score_threshold to limit results. Many country-specific recognisers are disabled by default and need enabling in the registry YAML
  5. Keep the containers on a private network or behind your own authenticating proxy. They accept any caller

Questions

Which is better for AI agents, Llama Guard 4 or Presidio?

Presidio scores 66 (B) on agent readiness against Llama Guard 4's 49.1 (D), and leads in 6 of 7 scored categories.

Can an agent call Llama Guard 4 and Presidio without installing anything?

No hosted endpoint is listed for Llama Guard 4. No hosted endpoint is listed for Presidio.

Are Llama Guard 4 and Presidio open source?

No open-source release is listed for Llama Guard 4. Presidio is open source (MIT).

Other comparisons with Llama Guard 4 or Presidio

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report