granite-guardian-3.3

About

What granite-guardian-3.3 is

Granite Guardian 3.3 8B Model Summary: Granite Guardian 3.3 8b is a specialized Granite 3.3 8B model designed to judge if the input prompts and the output responses of an LLM based system meet specified criteria. The model comes pre-baked with certain criteria including but not limited to: jailbreak attempts, profanity, and hallucinations related to tool calls and retrieval augmented generation in agent-based systems. Additionally, the model also allows users to bring their own criteria and tailor the judging behavior to specific use-cases. This version of Granite Guardian is a hybrid thinking model that allows the user to operate in thinking or non-thinking model. In thinking mode, the model produces detailed reasoning traces though <think ... </think and <score ... </score tags. In non-thinking mode, the model only produces the judgement score though the <score ... </score tags. It is trained on unique data comprising human annotations and synthetic data informed by internal red-teaming. It outperforms other open-source models in the same space on standard benchmarks. - Developers: IBM Research - GitHub Repository: ibm-granite/granite-guardian - Cookbook: Granite Guardian Recipes - Website: Granite Guardian Docs - Paper: Granite Guardian - Release Date: August 1, 2025 - License: Apache 2.0 Usage Quickstart Examples The model is pre-baked with certain judging criteria (see the section titled Definitions for Pre-baked Criteria for the complete list). We will now see a few examples of how to use the pre-baked criteria as well as how users can specify their own criteria. We will also see how to activate thinking mode. Let us setup the imports, load the model and a utility function to parse the model outputs including reasoning traces or chain-of-thought. Example 1: Detect jailbreak attempts in prompts Here we will set "criteriaid": "jailbreak" in the guardianconfig object that is passed to applychattemplate method. Example 2: Tool-call hallucination in a model's response Here we will set "criteriaid": "functioncall" in the guardianconfig object that is passed to applychattemplate method. Example 3: Detect lack of groundedness of model's response in RAG settings He

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys granite-guardian-3-3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (granite-guardian-3-3 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"granite-guardian-3-3","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Papers

Licence

Open weights

Sources

Weights & code

Explore

More language models