Sold by: IBM Data and AIÂ
Deployed on AWS
IBM Granite Guardian 3.2 5B is a streamlined AI model designed to detect risks in prompts and responses, enhancing safety and efficiency.
Overview
IBM Granite Guardian 3.2 5B is a specialized model for risk detection in prompts, responses, and multi-turn conversations. Built on instruction-tuned Granite language models and informed by IBM's Risk Atlas, it identifies harms such as hate, violence, and misinformation across diverse enterprise scenarios. It supports use cases like AI guardrails, RAG validation (context relevance, groundedness, answer relevance), and function call assessment within agentic workflows. Trained on a mix of human-annotated and red-teamed synthetic data, it outperforms peer models on safety benchmarks. Released under Apache 2.0, it aligns with IBM's AI Ethics principles.
Highlights
- Granite Guardian 3.2 5B excels in identifying various risks in prompts and responses, including social bias, jailbreaking, violence, profanity, sexual content, unethical behavior, harm engagement, and evasiveness. It also assesses hallucination risks in RAG pipelines, such as context relevance, groundedness, and answer relevance.
- Through iterative pruning and healing, approximately 30% of the original parameters were removed from the model, resulting in faster inference and lower resource consumption without compromising performance. It outperforms other open-source models in standard benchmarks.
- Designed for diverse enterprise applications, Granite Guardian 3.2 5B is effective in detecting harm-related risks within prompt text, model responses, or conversations. It also evaluates function calling risks within agentic workflows, assessing intermediate steps for syntactic and semantic hallucinations.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g5.12xlarge Inference (Batch) Recommended | Model inference on the ml.g5.12xlarge instance type, batch mode | $0.00 |
ml.g6e.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6e.2xlarge instance type, real-time mode | $0.00 |
ml.g5.24xlarge Inference (Batch) | Model inference on the ml.g5.24xlarge instance type, batch mode | $0.00 |
ml.g6e.4xlarge Inference (Real-Time) | Model inference on the ml.g6e.4xlarge instance type, real-time mode | $0.00 |
ml.g6e.12xlarge Inference (Real-Time) | Model inference on the ml.g6e.12xlarge instance type, real-time mode | $0.00 |
ml.g6e.16xlarge Inference (Real-Time) | Model inference on the ml.g6e.16xlarge instance type, real-time mode | $0.00 |
ml.g6e.24xlarge Inference (Real-Time) | Model inference on the ml.g6e.24xlarge instance type, real-time mode | $0.00 |
ml.g6e.48xlarge Inference (Real-Time) | Model inference on the ml.g6e.48xlarge instance type, real-time mode | $0.00 |
ml.p4d.24xlarge Inference (Real-Time) | Model inference on the ml.p4d.24xlarge instance type, real-time mode | $0.00 |
ml.p5.48xlarge Inference (Real-Time) | Model inference on the ml.p5.48xlarge instance type, real-time mode | $0.00 |
Vendor refund policy
This model is provided by IBM completely free of charge. No payment is required to use it. Therefore, there are no purchases to refund.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
IBM Granite Guardian 3.2 5B is now available under the Apache 2.0 license for both research and commercial use. This release introduces a refined architecture with reduced parameter count for faster inference, enhanced risk detection capabilities across multiple dimensions, and improved performance on industry-standard safety benchmarks. It supports key enterprise use cases including AI guardrails, RAG validation, and agentic workflow monitoring.
Additional details
Inputs
- Summary
The model can be invoked by passing a prompt. Please see the sample notebook for details.
- Input MIME type
- application/json
https://github.com/ibm-granite-community/SageMaker/blob/main/granite-guardian-3.2-5b/real_time_sample_input_data.json
https://github.com/ibm-granite-community/SageMaker/blob/main/granite-guardian-3.2-5b/batch_sample_input_data.json
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
inputs | The prompt to be passed to the model. | - | Yes |
Resources
Vendor resources
Support
Vendor support
Support is not provided for this product.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
IBM Granite 3.2 Instruct is an open-source model with controllable reasoning, offering strong performance and enhanced complex thinking.
IBM QRadar SIEM empowers security analysts and security operations teams with the visibility, automation and insights needed to quickly detect anomalies and uncover advanced threats in real-time.
IBM Granite 8B Code Instruct 128K is a model fine-tuned to solve long-context problems while maintaining short-context performance.
IBM Verify Identity Access helps you simplify your users' access while more securely adopting web, mobile and cloud technologies.
IBM Granite TimeSeries TTM is a compact pre-trained model with less than 1 million parameters for multivariate time-series forecasting.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.