SkillsHooksPromptsAgentsPersonasModelsPoliciesToolsTemplatesBundlesCategoriesStart here
← Models
Mo modelreasoningaistable

granite4.1-guardian

Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm criteria.

id model/granite4.1-guardianvendor IBMfamily Granite
Sizes
8b
Capabilities
toolsthinking
Model card
https://ollama.com/library/granite4.1-guardian ↗

Providers

ProviderModel idGet itTagsPullsUpdated
Ollama ↗granite4.1-guardianollama pull granite4.1-guardian1613.8K2026-06-10

Same family

ollamalocaltoolsthinking
Author IBM. Source ollama.com/library (original ↗). License unknown — the source states none; review before redistributing. Imported 2026-09-03. Description, capabilities, sizes, pulls, tag count and updated date as shown on the Ollama library page. Vendor, family and task are inferred from the model name; weights license is not published on the listing.