# Granite Guardian vs LlamaFirewall

> Granite Guardian scores 60.1 (C) on agent readiness against LlamaFirewall's 50.8 (D), and leads in every scored category. Both do guard injection. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/granite-guardian-vs-llamafirewall
- Markdown: https://www.anchorterminal.com/compare/granite-guardian-vs-llamafirewall.md (~2,700 tokens)
- Slim: https://www.anchorterminal.com/compare/granite-guardian-vs-llamafirewall.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/granite-guardian-vs-llamafirewall.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-09

Granite Guardian scores 60.1 (C) on agent readiness against LlamaFirewall's 50.8 (D), and leads in every scored category. Both do guard injection.

- Granite Guardian: grade C, 60.1/100, rank #478 of 842. Markdown https://www.anchorterminal.com/tools/granite-guardian.md · JSON https://www.anchorterminal.com/api/v1/tools/granite-guardian.json
- LlamaFirewall: grade D, 50.8/100, rank #682 of 842. Markdown https://www.anchorterminal.com/tools/llamafirewall.md · JSON https://www.anchorterminal.com/api/v1/tools/llamafirewall.json

## Which one, for what

### Granite Guardian (C)

Good for: A team with a GPU that wants one English-language judge for harm, jailbreaks, RAG groundedness, function-call checks and house rules, under a permissive licence with no gate.

Ahead on:
- Schema & documentation, 60 against 49
- Agent ergonomics, 69 against 60
- Payments & pricing, 60 against 50
- Maintenance & community, 47 against 15
- Transparency & trust, 70 against 58

Watch for: Trained and tested on English only, per the model card

### LlamaFirewall (D)

Good for: A Python agent team that wants injection, hidden-character and generated-code checks in process, is willing to pin dependencies or install from main, and can get the gated weights.

Also in its favour:
- Open source

Watch for: No PyPI release since 1.0.3 on 29 May 2025, and no changelog, tags or deprecation notes were found


## Score by category

| Category | Weight | Granite Guardian | LlamaFirewall | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 56 | 53 | Granite Guardian +3 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 60 | 49 | Granite Guardian +11 |
| Agent ergonomics | 13% (16.2 this run) | 69 | 60 | Granite Guardian +9 |
| Security & auth | 14% (17.5 this run) | 58 | 56 | Granite Guardian +2 |
| Payments & pricing | 10% (12.5 this run) | 60 | 50 | Granite Guardian +10 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 47 | 15 | Granite Guardian +32 |
| Transparency & trust | 7% (8.8 this run) | 70 | 58 | Granite Guardian +12 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **60.1 · C** | **50.8 · D** | |

## Facts side by side

| Fact | Granite Guardian | LlamaFirewall |
| --- | --- | --- |
| Kind | Model API | Agent framework |
| Vendor | IBM | Meta |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache 2.0 for the weights and the repository | MIT (library). The Prompt Guard 2 weights it downloads are under the Llama 4 Community Licence |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-04-29 | 2025-05-29 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Popularity | 182 stars | 4.4k stars, 1k PyPI/wk |

## Verdicts

**Granite Guardian.** One ungated Apache 2.0 model judges harm, jailbreaks, RAG groundedness, function-call errors and custom criteria, with signed weights and published evaluation code. It is trained and tested on English only, each call checks one criterion, the 4.1 prompt format differs from 3.x, and IBM's watsonx.ai lists only the deprecated 3.0 model.

**LlamaFirewall.** One `scan()` call runs several checks on the owner's machine and returns a short typed result. The last PyPI release is 1.0.3 from 29 May 2025, and its Prompt Guard loader imports a `huggingface_hub` class that current versions no longer export, so a fresh install needs older pins. The classifier weights also need Meta's manual approval.

## Before you call either

### Granite Guardian

1. Append the `<guardian>` block as the final user message, with the mode line, `### Criteria:` and `### Scoring Schema:`. Copy the strings from the model card, because no package builds them
2. Use the no-think instruction for gating and parse `<score>`. Think mode writes a reasoning trace first, and the card's examples allow up to 2,048 output tokens
3. Treat `yes` as the criterion being met, which for built-in criteria means the risk is present. Treat a missing `<score>` tag as a failed check
4. Pass retrieved text through `documents=` and tool schemas through `available_tools=` in `apply_chat_template`, not inside the message text
5. Under Ollama, set `num_ctx` in the request options. IBM's docs say the default context is short and long requests are truncated

### LlamaFirewall

1. Pin `huggingface_hub` below 1.0 and a matching `transformers` 4.x before importing the Prompt Guard scanner from the 1.0.3 wheel, or install from main
2. Get access to `meta-llama/Llama-Prompt-Guard-2-86M` and set a Hugging Face token first. Without one the loader prompts for a login and a headless run stalls
3. Call `scan_async` inside a running event loop. `scan()` wraps `asyncio.run` and fails there. `scan_async` returns score 0.0 and reason `default` on every allow
4. Split text longer than 512 tokens yourself before a Prompt Guard scan. The library truncates and does not chunk
5. Do not feed a block `reason` back to the model. The Prompt Guard reason quotes the full scanned text, and the hidden ASCII reason decodes the hidden payload

## Questions

### Which is better for AI agents, Granite Guardian or LlamaFirewall?

Granite Guardian scores 60.1 (C) on agent readiness against LlamaFirewall's 50.8 (D), and leads in every scored category.

### Can an agent call Granite Guardian and LlamaFirewall without installing anything?

No hosted endpoint is listed for Granite Guardian. No hosted endpoint is listed for LlamaFirewall.

### Are Granite Guardian and LlamaFirewall open source?

No open-source release is listed for Granite Guardian. LlamaFirewall is open source (MIT (library). The Prompt Guard 2 weights it downloads are under the Llama 4 Community Licence).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/granite-guardian-vs-llamafirewall.json, and with the fewest tokens: https://www.anchorterminal.com/compare/granite-guardian-vs-llamafirewall.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "granite-guardian", "b": "llamafirewall"}`. From a terminal: `anchor compare granite-guardian llamafirewall`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/granite-guardian.json and https://www.anchorterminal.com/api/v1/tools/llamafirewall.json

## Other comparisons with Granite Guardian or LlamaFirewall

- [Amazon Bedrock Guardrails vs Granite Guardian](https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-granite-guardian.md)
- [Amazon Bedrock Guardrails vs LlamaFirewall](https://www.anchorterminal.com/compare/amazon-bedrock-guardrails-vs-llamafirewall.md)
- [Azure AI Content Safety (Prompt Shields) vs Granite Guardian](https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-granite-guardian.md)
- [Azure AI Content Safety (Prompt Shields) vs LlamaFirewall](https://www.anchorterminal.com/compare/azure-ai-content-safety-vs-llamafirewall.md)
- [Cisco AI Defense Inspection API vs Granite Guardian](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-granite-guardian.md)
- [Cisco AI Defense Inspection API vs LlamaFirewall](https://www.anchorterminal.com/compare/cisco-ai-defense-inspection-vs-llamafirewall.md)
- [Google Cloud Model Armor vs Granite Guardian](https://www.anchorterminal.com/compare/google-model-armor-vs-granite-guardian.md)
- [Google Cloud Model Armor vs LlamaFirewall](https://www.anchorterminal.com/compare/google-model-armor-vs-llamafirewall.md)
- [Guardrails AI vs LlamaFirewall](https://www.anchorterminal.com/compare/guardrails-ai-vs-llamafirewall.md)
- [Lakera Guard (Check Point AI Guardrails) vs LlamaFirewall](https://www.anchorterminal.com/compare/lakera-guard-vs-llamafirewall.md)
- [LlamaFirewall vs NVIDIA NeMo Guardrails](https://www.anchorterminal.com/compare/llamafirewall-vs-nemo-guardrails.md)
- [LlamaFirewall vs OpenAI Guardrails](https://www.anchorterminal.com/compare/llamafirewall-vs-openai-guardrails.md)
- [LlamaFirewall vs Prisma AIRS AI Runtime Security API](https://www.anchorterminal.com/compare/llamafirewall-vs-prisma-airs.md)
- [Granite Guardian vs Guardrails AI](https://www.anchorterminal.com/compare/granite-guardian-vs-guardrails-ai.md)
- [Granite Guardian vs Lakera Guard (Check Point AI Guardrails)](https://www.anchorterminal.com/compare/granite-guardian-vs-lakera-guard.md)
- [Granite Guardian vs Llama Guard 4](https://www.anchorterminal.com/compare/granite-guardian-vs-llama-guard.md)
- [Granite Guardian vs Mistral Moderation API](https://www.anchorterminal.com/compare/granite-guardian-vs-mistral-moderation.md)
- [Granite Guardian vs NVIDIA NeMo Guardrails](https://www.anchorterminal.com/compare/granite-guardian-vs-nemo-guardrails.md)
- [Granite Guardian vs OpenAI Guardrails](https://www.anchorterminal.com/compare/granite-guardian-vs-openai-guardrails.md)
- [Granite Guardian vs OpenAI Moderation API](https://www.anchorterminal.com/compare/granite-guardian-vs-openai-moderation.md)
- [Granite Guardian vs Prisma AIRS AI Runtime Security API](https://www.anchorterminal.com/compare/granite-guardian-vs-prisma-airs.md)
- [LlamaFirewall vs Presidio](https://www.anchorterminal.com/compare/llamafirewall-vs-microsoft-presidio.md)
- [LlamaFirewall vs Mistral Moderation API](https://www.anchorterminal.com/compare/llamafirewall-vs-mistral-moderation.md)
- [Granite Guardian vs Presidio](https://www.anchorterminal.com/compare/granite-guardian-vs-microsoft-presidio.md)
- [Llama Guard 4 vs LlamaFirewall](https://www.anchorterminal.com/compare/llama-guard-vs-llamafirewall.md)