The open source family of Granite models are lightweight, low-cost/no-cost LLMs and tools that help developers swiftly prototype ideas before scaling them on production systems.
29 January 2026
Article
Learn how fine‑tuning a small language model (Mistral 7B) and using a Granite 3.3 8B orchestrator solves the consistency challenges of large‑scale business document evaluation.
08 October 2025
Article
Learn about using Granite models and watsonx for enterprise AI with Java. Understand the importance of openness, interoperability, and long-term support in AI adoption. Granite models provide an open foundation for AI, while watsonx delivers enterprise governance and lifecycle management. The combination of Quarkus, LangChain4j, Jakarta EE, and Red Hat OpenShift AI provides a complete story for confident AI adoption. This approach aligns AI adoption with the principles that made Java successful, ensuring investments remain valuable over time.
24 September 2025
Article
In this article, we demonstrate using different prompts with different contexts to analyze how LLMs behave when asked generic-related questions. We show how the Granite 3.3-2b model is good at identifying associated quantifiers in generic phrases and the model's responses are context-driven too.
14 August 2025
Article
InstructLab empowers developers to unleash the full potential of LLMs, offering a streamlined training process, cost-efficiency, community collaboration, and stability in model performance.
01 August 2025
Article
Explore how generative AI helps financial services meet EU AI Act compliance with transparency, risk management, and regulatory automation tools.
10 July 2025
Article
Boost mainframe DevOps with AI tools such as watsonx Code Assistant for Z and IBM Test Accelerator for Z for COBOL refactoring, Java transformation, automated testing, and z/OS modernization.
17 June 2025
Article
The Data Prep Kit (DPK) offers a diverse set of pre-built transforms to streamline data preparation for AI applications. These transforms cater to various data formats, including text, code, and structured data. These built-in transforms provide a strong foundation for handling common data processing tasks. This rich collection of built-in transforms empowers one to efficiently prepare the data for various AI and machine learning applications.
28 February 2025
Article
Learn how open source impacts watsonx through some of the key open source projects that IBM has invested in.
17 February 2025
Article
Explore new AI agents, watsonx assistants, open source tools, IBM foundation models, and AI applications with AI experts.
31 January 2025
Article
Discover how cache augmented generation (CAG) boosts language model efficiency by preloading knowledge, reducing latency, and improving response accuracy.
11 December 2024
Article
Explore IBM RAG DA to deploy secure, scalable, and customizable Retrieval Augmented Generation solutions with AI, Watsonx, and generative AI technologies.
15 October 2024
Article
Create a specialised LLM using the Low-Rank Adaption (LoRA) transformer technique and Optuna library for a question answering task
