AI Potluck
Product / UX / Safety & Guardrails

Granite Guardian

IBM

IBM's open guardrail model family for detecting risks in prompts and responses, plus RAG-specific checks. It covers harm, social bias, jailbreaking, violence, profanity and sexual content, and adds hallucination checks for retrieval pipelines (context relevance, groundedness, answer relevance).

Granite Guardian 3.2 (5B, distilled from the 8B); Apache-2.0 open weights. ~1.4K HF downloads/month, 14 likes (June 2026). Verified live June 2026.

Openness

4 medium confidence
4.0
weights
open(granite-guardian-3.2-5b on HF)
data
not-released
license
Apache-2.0(OSI)

Open weights under Apache-2.0 (permissive, OSI), but the training data is not released, so it stops short of the open_source (5) tier; a strong open_weights release at 4.

Adoption

2 medium confidence
2.0

~1.4K HF downloads/month on the 3.2-5B variant (June 2026); cumulative across the Guardian family is higher. Enterprise-leaning distribution via watsonx.

Capability

4 medium confidence
4.0

One of the broadest open guardrails: standard harm taxonomy plus RAG-specific groundedness/hallucination checks.

Unchanged since 2026-06-29 (last edited, not re-checked)