In IBM watsonx.ai, you can use IBM foundation models that are built with integrity and designed for business.
The Granite family of IBM foundation models includes decoder-only models that can efficiently predict and generate language.
The models were built with trusted data that has the following characteristics:
- Sourced from quality data sets in domains such as finance (SEC Filings), law (Free Law), technology (Stack Exchange), science (arXiv, DeepMind Mathematics), literature (Project Gutenberg (PG-19)), and more.
- Compliant with rigorous IBM data clearance and governance standards.
- Scrubbed of hate, abuse, and profanity, data duplication, and blocklisted URLs, among other things.
IBM is committed to building AI that is open, trusted, targeted, and empowering. For more information about contractual protections that are related to IBM indemnification, see the IBM Client Relationship Agreement and IBM watsonx.ai service description.
The following foundation models from IBM are available in watsonx.ai:
- granite-3-2-8b-instruct
- granite-3-2-8b-instruct-preview-rc
- granite-3-2b-instruct
- granite-3-8b-instruct
- granite-3-8b-base
- granite-7b-lab
- granite-8b-japanese
- granite-13b-chat-v2
- granite-13b-instruct-v2
- granite-20b-multilingual
- granite-3b-code-instruct
- granite-8b-code-instruct
- granite-20b-code-instruct
- granite-20b-code-base-schema-linking
- granite-20b-code-base-sql-gen
- granite-34b-code-instruct
- granite-guardian-3-2b
- granite-guardian-3-8b
- granite-ttm-512-96-r2
- granite-ttm-1024-96-r2
- granite-ttm-1536-96-r2
- granite-vision-3-2-2b
For details about third-party foundation models, see Third-party foundation models.
For information about the GPU requirements for the supported foundation models, see Foundation models.
The following sections provide more information and extra resources for learning about each model.
granite-3-2-8b-instruct
Granite 3.2 Instruct is a long-context foundation model that is fine tuned for enhanced reasoning capabilities. The thinking capability is configurable, which means you can control when reasoning is applied.
- Usage
-
Capable of common generative tasks, including code-related tasks, function-calling, and multilingual dialogs. Specializes in reasoning and long-context tasks such as summarizing long document or meeting transcripts and responding to questions with answers that are grounded in context provided from long documents.
- Size
-
8 billion parameters
- API pricing tier
-
Class 12
- Availability
-
Provided by IBM deployed on multitenant hardware.
- Token limits
-
Context window length (input + output): 131,072
Note: The maximum new tokens, which means the tokens generated by the foundation model per request, is limited to 16,384.
- Supported natural languages
-
English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese
- Instruction tuning information
-
Built on top of Granite-3.1-8B-Instruct, it was trained using a mix of permissively licensed open-source datasets and internally generated synthetic data designed for reasoning tasks.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
Granite 3.2 8b Instruct Preview 
Tech preview of the Granite 3.2 Instruct long-context foundation model that is fine tuned for enhanced reasoning capabilities. The thinking capability is configurable, which means you can control when reasoning is applied.
- Usage
-
Capable of common generative tasks, including code-related tasks, function-calling, and multilingual dialogs. Specializes in reasoning and long-context tasks such as summarizing long document or meeting transcripts and responding to questions with answers that are grounded in context provided from long documents.
- Size
-
8 billion parameters
- API pricing tier
-
No charge during the tech preview release.
- Availability
-
Provided by IBM deployed on multitenant hardware.
- Token limits
-
Context window length (input + output): 131,072
Note: The maximum new tokens, which means the tokens generated by the foundation model per request, is limited to 16,384.
- Supported natural languages
-
English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese
- Instruction tuning information
-
Built on top of Granite-3.1-8B-Instruct, it was trained using a mix of permissively licensed open-source datasets and internally generated synthetic data designed for reasoning tasks.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
Granite Instruct 3.1 models
The Granite Instruct foundation models belong to the IBM Granite family of models. The granite-3-2b-instruct and granite-3-8b-instruct foundation models are Granite 3.1 Instruct foundation models. These models build on earlier iterations to provide better support for coding tasks and intrinsic functions for agents.
- Usage
-
Granite Instruct foundation models are designed to excel in instruction-following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.
- Sizes
-
- 2 billion parameters
- 8 billion parameters
- API pricing tier
-
- 2b: Class C1
- 8b: Class 12
For pricing details, see Table 2.
- Availability
-
Provided by IBM deployed on multitenant hardware.
- Try it out
-
Experiment with samples:
- Token limits
-
Context window length (input + output)
- 2b: 131,072
- 8b: 131,072
The maximum new tokens, which means the tokens generated by the foundation model per request, is limited to 8,192.
- Supported natural languages
-
English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, Chinese (Simplified).
- Supported programming languages
-
The Granite Instruct models are trained with code written in 116 programming languages.
- Instruction tuning information
-
The Granite Instruct models are fine tuned Granite Instruct base models trained on over 12 trillion tokens with a combination of permissively licensed open-source and proprietary instruction data.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
granite-3-8b-base
The Granite 8b foundation model is a base model that belongs to the IBM Granite family of models. The model is trained on 10 trillion tokens that are sourced from diverse domains, and then further trained on 2 trillion tokens of high-quality data that was carefully chosen to enhance the model's performance on specific tasks.
- Usage
-
The Granite 3.0 base foundation model is a baseline model that you can customize to create specialized models for specific application scenarios.
- Size
-
8 billion parameters
- API pricing tier
-
For pricing details, see Table 4.
- Availability
-
Deploy on demand for dedicated use.
- Token limits
-
Context window length (input + output): 4,096
- Supported natural languages
-
English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, Chinese (Simplified).
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
granite-7b-lab
The granite-7b-lab foundation model is provided by IBM. The granite-7b-lab foundation model uses a novel alignment tuning method from IBM Research. Large-scale Alignment for chatBots, or LAB is a method for adding new skills to existing foundation models by generating synthetic data for the skills, and then using that data to tune the foundation model.
- Usage
-
Supports general purpose tasks, including extraction, summarization, classification, and more. Follow the prompting guidelines for tips on usage. For more information, see Prompting granite-7b-lab.
- Size
-
7 billion parameters
- API pricing tier
-
For pricing details, see Table 4.
- Availability
-
Deploy on demand for dedicated use.
- Try it out
- Token limits
-
Context window length (input + output): 8,192
Note: The maximum new tokens, which means the tokens generated by the foundation model per request, is limited to 4,096.
- Supported natural languages
-
English
- Instruction tuning information
-
The granite-7b-lab foundation model is trained iteratively by using the large-scale alignment for chatbots (LAB) methodology.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
granite-8b-japanese
The granite-8b-japanese model is provided by IBM. The granite-8b-japanese foundation model is an instruct variant initialized from the pre-trained Granite Base 8 Billion Japanese model and is trained to understand and generate Japanese text.
- Usage
-
Useful for general purpose tasks in the Japanese language, such as classification, extraction, question-answering, and for language translation between Japanese and English.
- Size
-
8 billion parameters
- API pricing tier
-
Class 1. For pricing details, see Table 2.
- Availability
-
Provided by IBM deployed on multitenant hardware in the Tokyo data center.
- Try it out
-
Experiment with samples:
- Token limits
-
Context window length (input + output): 4,096
- Supported natural languages
-
English, Japanese
- Instruction tuning information
-
The Granite family of models is trained on enterprise-relevant datasets from five domains: internet, academic, code, legal, and finance. The granite-8b-japanese model was pretrained on 1 trillion tokens of English and 0.5 trillion tokens of Japanese text.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
granite-13b-chat-v2
The granite-13b-chat-v2 model is provided by IBM. This model is optimized for dialog use cases and works well with virtual agent and chat applications.
Usage: Generates dialog output like a chatbot. Uses a model-specific prompt format. Includes a keyword in its output that can be used as a stop sequence to produce succinct answers. Follow the prompting guidelines for tips on usage. For more information, see Prompting granite-13b-chat-v2.
- Size
-
13 billion parameters
- API pricing tier
- Availability
-
- Deploy on demand for dedicated use.
- Try it out
- Token limits
-
Context window length (input + output): 8,192
- Supported natural languages
-
English
- Instruction tuning information
-
The Granite family of models is trained on enterprise-relevant datasets from five domains: internet, academic, code, legal, and finance. Data used to train the models first undergoes IBM data governance reviews and is filtered of text that is flagged for hate, abuse, or profanity by the IBM-developed HAP filter. IBM shares information about the training methods and datasets used.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
granite-13b-instruct-v2
The granite-13b-instruct-v2 model is provided by IBM. This model was trained with high-quality finance data, and is a top-performing model on finance tasks. Financial tasks evaluated include: providing sentiment scores for stock and earnings call transcripts, classifying news headlines, extracting credit risk assessments, summarizing financial long-form text, and answering financial or insurance-related questions.
- Usage
-
Supports extraction, summarization, and classification tasks. Generates useful output for finance-related tasks. Uses a model-specific prompt format. Accepts special characters, which can be used for generating structured output.
- Size
-
13 billion parameters
- API pricing tier
- Availability
-
- Provided by IBM deployed on multitenant hardware.
- Deploy on demand for dedicated use.
- Try it out
-
Experiment with samples:
- Token limits
-
Context window length (input + output): 8,192
Note: The maximum new tokens, which means the tokens generated by the foundation model per request, is limited to 4,096.
- Supported natural languages
-
English
- Instruction tuning information
-
The Granite family of models is trained on enterprise-relevant datasets from five domains: internet, academic, code, legal, and finance. Data used to train the models first undergoes IBM data governance reviews and is filtered of text that is flagged for hate, abuse, or profanity by the IBM-developed HAP filter. IBM shares information about the training methods and datasets used.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
granite-20b-multilingual
A foundation model from the IBM Granite family. The granite-20b-multilingual foundation model is based on the Granite Base 20 billion base model and is trained to understand and generate text in English, German, Spanish, French, and Portuguese.
- Usage
-
English, German, Spanish, French, and Portuguese closed-domain question answering, summarization, generation, extraction, and classification.
Note:
This foundation model supports skills that are contributed by the open source community from InstructLab.
- Size
-
20 billion parameters
- API pricing tier
-
Class 1. For pricing details, see Table 2.
- Availability
-
Provided by IBM deployed on multitenant hardware.
This model is deprecated. See Foundation model lifecycle.
- Try it out
- Token limits
-
Context window length (input + output): 8,192
- Supported natural languages
-
English, German, Spanish, French, and Portuguese
- Instruction tuning information
-
The Granite family of models is trained on enterprise-relevant datasets from five domains: internet, academic, code, legal, and finance. Data used to train the models first undergoes IBM data governance reviews and is filtered of text that is flagged for hate, abuse, or profanity by the IBM-developed HAP filter. IBM shares information about the training methods and datasets used.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
Granite Code models
Foundation models from the IBM Granite family. The Granite Code foundation models are instruction-following models fine-tuned using a combination of Git commits paired with human instructions and open-source synthetically generated code instruction datasets.
The granite-8b-code-instruct v2.0.0 foundation model can process larger prompts with an increased context window length.
- Usage
-
The following Granite Code foundation models are designed to respond to coding-related instructions and can be used to build coding assistants:
- granite-3b-code-instruct
- granite-8b-code-instruct
- granite-20b-code-instruct
- granite-34b-code-instruct
The following Granite Code foundation models are instruction-tuned versions of the granite-20b-code-base foundation model that are designed for text-to-SQL generation tasks.
- granite-20b-code-base-schema-linking
- granite-20b-code-base-sql-gen
- Sizes
-
- 3 billion parameters
- 8 billion parameters
- 20 billion parameters
- 34 billion parameters
- API pricing tier
-
Class 1.
For pricing details for the provided code models, see Table 2.
For pricing details for the deploy on demand models, see Table 4.
- Availability
-
All code models, except the text-to-SQL models: Provided by IBM deployed on multitenant hardware.
All code models, including the text-to-SQL foundation models: Deploy on demand for dedicated use.
- Try it out
-
Experiment with samples:
- Token limits
-
Context window length (input + output)
-
granite-3b-code-instruct : 128,000
When the model runs in the multitenant environment only, a maximum new tokens limit is applied, which means the tokens generated by the foundation model per request, is limited to 8,192.
-
granite-8b-code-instruct : 128,000
When the model runs in the multitenant environment only, a maximum new tokens limit is applied, which means the tokens generated by the foundation model per request, is limited to 8,192.
-
granite-20b-code-instruct : 8,192
The maximum new tokens, which means the tokens generated by the foundation model per request, is limited to 4,096.
-
granite-20b-code-base-schema-linking : 8,192
-
granite-20b-code-base-sql-gen : 8,192
-
granite-34b-code-instruct : 8,192
-
- Supported natural languages
-
English
- Supported programming languages
-
The Granite Code foundation models support 116 programming languages including Python, Javascript, Java, C++, Go, and Rust. For the full list, see IBM foundation models.
- Instruction tuning information
-
These models were fine-tuned from Granite Code base models on a combination of permissively licensed instruction data to enhance instruction-following capabilities including logical reasoning and problem-solving skills.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
- Granite Code models research paper
- Scaling Granite Code models research paper
- 3b Model card (Multitenant)
- 3b Model card (Dedicated)
- 8b Model card (Multitenant)
- 8b Model card (Dedicated)
- 20b Model card (Multitenant)
- 20b Model card (Dedicated)
- 20b base schema linking model card (Dedicated)
- 20b base SQL gen model card (Dedicated)
- 34b Model card (Multitenant)
- 34b Model card (Dedicated)
Granite Guardian models
The Granite Guardian foundation models belong to the IBM Granite family of models. The granite-guardian-3-2b and granite-guardian-3-8b foundation models are fine-tuned Granite Instruct models that are designed to detect risks in prompts and responses. The foundation models help with risk detection along many key dimensions in the AI Risk Atlas.
The generation 3.1 version of the models are trained on a combination of human-annotated and additional synthetic data to improve performance for risks related to hallucination and jailbreak.
- Usage
-
Granite Guardian foundation models are designed to detect harm-related risks within prompt text or model response (as guardrails) and can be used in retrieval-augmented generation use cases to assess context relevance (whether the retrieved context is relevant to the query), groundedness (whether the response is accurate and faithful to the provided context), and answer relevance (whether the response directly addresses the user's query).
- Sizes
-
- 2 billion parameters
- 8 billion parameters
- API pricing tier
-
- 2b: Class C1
- 8b: Class 12
For pricing details, see Table 2.
- Availability
-
Provided by IBM deployed on multitenant hardware.
- Try it out
-
Experiment with samples:
- Token limits
-
Context window length (input + output)
- 2b: 131,072
- 8b: 131,072
Note: The maximum new tokens, which means the tokens generated by the foundation model per request, is limited to 8,192.
- Supported natural languages
-
English
- Instruction tuning information
-
The Granite Guardian models are fine tuned Granite Instruct models trained on a combination of human annotated and synthetic data.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
Granite time series models
Granite time series foundation models belong to the IBM Granite family of models. These models are compact, pretrained models for multivariate time series forecasting from IBM Research. The following versions are available to use for data forecasting in watsonx.ai:
- granite-ttm-512-96-r2
- granite-ttm-1024-96-r2
- granite-ttm-1536-96-r2
- Usage
-
You can apply one of these pretrained models on your target data to get an initial forecast without having to train the model on your data. When given a set of historic, timed data observations, the Granite time series foundation models can apply their understanding of dynamic systems to forecast future data values. These models work best with data points in minute or hour intervals and generate a forecast dataset with up to 96 data points per target channel.
- Size
-
1 million parameters
- API pricing tier
-
- Input: Class 14
- Output: Class 15
For pricing details, see Resource unit metering for time series foundation models.
- Availability
-
Provided by IBM deployed on multitenant hardware.
- Try it out
- Context length
-
Required minimum data points per channel in the API request:
- granite-ttm-512-96-r2: 512
- granite-ttm-1024-96-r2: 1,024
- granite-ttm-1536-96-r2: 1,536
- Supported natural languages
-
English
- Instruction tuning information
-
The Granite time series models were trained on almost a billion samples of time series data from various domains, including electricity, traffic, manufacturing, and more.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
Granite Vision 3.2 2b
Granite Vision 3.2 2b is a image-to-text foundation model that is built for enterprise use cases. This multimodal Granite model is capable of ingesting images and text for tasks like understanding charts, diagrams, graphs, and more.
- Usage
-
The granite-vision-3-2-2b foundation model is designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
- Size
-
2 billion parameters
- API pricing tier
-
Class C1
- Availability
-
Provided by IBM deployed on multitenant hardware.
- Token limits
-
Context window length (input + output): 131,072
Note: The maximum new tokens, which means the tokens generated by the foundation model per request, is limited to 16,384.
- Supported natural languages
-
English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese
- Instruction tuning information
-
The granite-vision-3-2-2b foundation model was trained on a curated instruction-following dataset, comprising diverse public datasets and synthetic datasets tailored to support a wide range of document understanding and general image tasks. It was trained by fine-tuning the granite-3-2b-instruct foundation model with both image and text modalities.
- Model architecture
-
Decoder
- License
-
See the service descriptions for the two services that comprise watsonx.ai:
IBM-developed foundation models are considered part of the IBM Cloud Service. When you use an IBM-developed foundation model that is provided in watsonx.ai, the contractual protections related to IBM indemnification apply. For more information, see the IBM Client Relationship Agreement in addition to the service descriptions.
- Learn more
- Read the following resources:
IBM embedding models
Foundation models built by IBM include encoder-only models that specialize in natural language processing and text embedding tasks.
The following embedding models from IBM are available in watsonx.ai:
- granite-embedding-107m-multilingual
- A 384-dimension embedding model that converts text in multiple languages into text embeddings.
- granite-embedding-278m-multilingual
- A 384-dimension embedding model that converts text in multiple languages into text embeddings.
- slate-125m-english-rtrvr-v2, slate-125m-english-rtrvr
- 768-dimension embedding models that convert text into text embeddings.
- slate-30m-english-rtrvr-v2, slate-30m-english-rtrvr
- 384-dimension embedding models that convert text into text embeddings.
For more information about these models, see Supported encoder foundation models.
For more information about using IBM embedding models to convert sentences and passages into text embeddings, see Text embedding generation.
Natural Language Processing capabilities
IBM Slate models also power a set of libraries that you can use for common natural language processing (NLP) tasks, such as classification, entity extraction, sentiment analysis, and more.
For more information about how to use the NLP capabilities of the Slate models, see Watson NLP library.
Parent topic: Supported foundation models