IBM Granite

IBM Granite 3.1 is the latest update to our Granite series of open, performant, enterprise-optimized language models. This suite of improvements, additions and new capabilities focuses primarily on augmenting performance, accuracy and accountability in essential enterprise use cases like tool use, retrieval augmented generation (RAG) and scalable agentic AI workflows.

Granite 3.1 builds upon the momentum of the recently launched Granite 3.0 collection. IBM will continue to release updated models and functionality for the Granite 3 series in the coming months, with new multimodal capabilities slated for release in Q1 2025.

Here's the key info, at a glance:
 

• Granite 3.1 8B Instruct delivers significant performance improvements over Granite 3.0 8B Instruct. Its average score across the Hugging Face OpenLLM Leaderboard benchmarks is now among the highest of any open model in its weight class.

• We’ve expanded the context windows of the entire Granite 3 language model family. Our latest dense models (Granite 3.1 8B, Granite 3.1 2B), MoE models (Granite 3.1 3B-A800M, Granite 3.1 1B-A400M) and guardrail models (Granite Guardian 3.1 8B, Granite Guardian 3.1 2B) all feature a 128K token context length.

• We’re releasing a family of all-new embedding models. The new retrieval-optimized Granite Embedding models are offered in four sizes, ranging from 30M–278M parameters. Like their generative counterparts, they offer multilingual support across 12 different languages: English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch and Chinese.

• Granite Guardian 3.1 8B and 2B feature a new function calling hallucination detection capability, allowing increased control over and observability for agents making tool calls.

• All Granite 3.1, Granite Guardian 3.1, and Granite Embedding models are open source under Apache 2.0 license.

• These latest entries in the Granite series follow IBM’s recent launch of Docling (an open source framework for prepping documents for RAG and other generative AI applications) and Bee (an open source, model agnostic framework for agentic AI).

• Granite TTM (TinyTimeMixers), IBM’s series of compact but highly performant timeseries models, are now available in watsonx.ai through the beta release of watsonx.ai Timeseries Forecasting API and SDK.

• Granite 3.1 models are now available in IBM watsonx.ai, as well as through platform partners including (in alphabetical order) Docker, Hugging Face, LM Studio, Ollama and Replicate.

• Granite 3.1 will also be leveraged internally by enterprise partners: Samsung is integrating select Granite models into its SDS platform; Lockheed Martin is integrating Granite 3.1 models into its AI Factory tools, used by over 10,000 developers and engineers.

Read the full story.