Supported foundation models in watsonx.ai

You can work with third-party and IBM foundation models in IBM watsonx.ai.

How to choose a model

To review factors that can help you to choose a model, such as supported tasks and languages, see Choosing a model and Foundation model benchmarks.

Attention:

Model availability varies by data center location. For details, see Regional availability for services and features on IBM Cloud.

Provided foundation models that are ready to use

You can deploy foundation models from a collection of models curated by IBM in watsonx.ai. You can prompt these foundation models in the Prompt Lab or programmatically.

You can choose to deploy the following types of models:

IBM foundation models
Third-party foundation models

All IBM foundation models in watsonx.ai are indemnified by IBM.

For information about the GPU requirements for the supported foundation models, see Foundation models in IBM watsonx.ai in the IBM Software Hub documentation.

IBM foundation models

The following table lists the supported foundation models that IBM provides for inferencing. The foundation models must be deployed in your cluster by an administrator to be available for use. All IBM models are instruction-tuned.

Table 1. IBM foundation models in watsonx.ai for inferencing
Model name	Context window (input + output tokens)	Supported tasks	More information
granite-3-3-8b-instruct	131,072	• classification • extraction • generation • question answering • summarization • retrieval-augmented generation • code • extraction • translation • function calling	• Model card • Website
granite-13b-instruct-v2	8,192	• classification • extraction • generation • question answering • summarization	• Model card • Website • Research paper
granite-7b-lab	8,192	• classification • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Research paper (LAB)
granite-8b-japanese	4,096	• classification • extraction • generation • question answering • summarization • translation	• Model card • Website • Research paper
granite-3-2-8b-instruct	131,072	• classification • extraction • generation • question answering • summarization • retrieval-augmented generation • code • extraction • translation • function calling	• Model card • Website • Research paper
granite-3-2b-instruct	4,096	• classification • extraction • function calling • generation • question answering • summarization	• Model card • Website • Research paper
granite-3-8b-instruct	4,096	• classification • extraction • function calling • generation • question answering • summarization	• Model card • Website • Research paper
granite-guardian-3-2b	8,192	• classification • extraction • generation • question answering • summarization	• Model card • Website
granite-guardian-3-8b	8,192	• classification • extraction • generation • question answering • summarization	• Model card • Website
granite-3b-code-instruct	128,000	• code • classification • extraction • generation • question answering • summarization	• Model card • Website • Research paper
granite-8b-code-instruct	128,000	• code • classification • extraction • generation • question answering • summarization	• Model card • Website • Research paper
granite-20b-code-instruct	8,192	• code • classification • extraction • generation • question answering • summarization	• Model card • Research paper
granite-20b-code-base-schema-linking	8,192	• code	• Model card • Research paper
granite-20b-code-base-sql-gen	8,192	• code	• Model card • Research paper
granite-34b-code-instruct	8,192	• code • classification • extraction • generation • question answering • summarization	• Model card • Research paper
granite-vision-3-2-2b	131,072	• question answering	• Model card • Website • Research paper

Table 2. IBM foundation models provided with watsonx.ai for forecasting future values
Model name	Context length Min data points	More information
granite-ttm-512-96-r2	512	• Model card • Website • Research paper
granite-ttm-1024-96-r2	1,024	• Model card • Website • Research paper
granite-ttm-1536-96-r2	1,536	• Model card • Website • Research paper

Third-party foundation models

The following table lists the supported foundation models that are provided by third parties. An administrator must deploy the foundation models in your cluster before you can use these models.

Table 3. Supported third-party foundation models in watsonx.ai
Model name	Provider	Context window (input + output tokens)	Supported tasks	More information
allam-1-13b-instruct	National Center for Artificial Intelligence and Saudi Authority for Data and Artificial Intelligence	4,096	• classification • extraction • generation • question answering • retrieval-augmented generation • summarization • translation	• Model card
codestral-22b	Mistral AI	32,768	• code	• Model card • Blog post for Codestral
codestral-2501	Mistral AI	256,000	• code	• Blog post for Codestral 25.01 Note: You must purchase Mistral AI with IBM separately before you are entitled to use this model.
elyza-japanese-llama-2-7b-instruct	ELYZA, Inc	4,096	• classification • extraction • generation • question answering • retrieval-augmented generation • summarization • translation	• Model card • Blog on note.com
flan-t5-xl-3b	Google	4,096	• classification • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Research paper
flan-t5-xxl-11b	Google	4,096	• classification • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Research paper
flan-ul2-20b	Google	4,096	• classification • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • UL2 research paper • Flan research paper
jais-13b-chat	Inception, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), and Cerebras Systems	2,048	• classification • extraction • generation • question answering • retrieval-augmented generation • summarization • translation	• Model card • Research paper
llama-4-maverick-17b-128e-instruct-fp8	Meta	131,072	• classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization • translation • function calling	• Model card • Meta AI blog
llama-4-scout-17b-16e-instruct	Meta	131,072	• classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization • translation • function calling	• Model card • Meta AI blog
llama-3-3-70b-instruct	Meta	131,072	• classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog • Meta AI docs
llama-3-2-1b-instruct	Meta	131,072	• classification • code generation and conversion • extraction • function calling • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog • Research paper
llama-3-2-3b-instruct	Meta	131,072	• classification • code generation and conversion • extraction • function calling • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog • Research paper
llama-3-2-11b-vision-instruct	Meta	131,072	• classification • code generation and conversion • extraction • function calling • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog • Research paper
llama-3-2-90B-vision-instruct	Meta	131,072	• classification • code generation and conversion • extraction • function calling • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog • Research paper
llama-guard-3-11b-vision	Meta	131,072	• classification • code generation and conversion • extraction • function calling • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog • Research paper
llama-3-1-8b-instruct	Meta	131,072	• classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog
llama-3-1-70b-instruct	Meta	131,072	• classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog
llama-3-405b-instruct	Meta	16,384	• classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog
llama-3-8b-instruct	Meta	8,192	• classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog
llama-3-70b-instruct	Meta	8,192	• classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Meta AI blog
llama-2-13b-chat	Meta	4,096	• classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Research paper
llama2-13b-dpo-v7	Meta	4,096	• classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization	• Model card • Research paper (DPO)
ministral-8b-instruct	Mistral AI	128,000	• classification • code • extraction • generation • retrieval-augmented generation • summarization • translation • question answering • function calling	• Model card • Blog post for Ministral 8b Note: You must purchase Mistral AI with IBM separately before you are entitled to use this model.
mistral-large	Mistral AI	32,768	• classification • code • extraction • generation • retrieval-augmented generation • summarization • translation	• Model card • Blog post for Mistral Large 2 Note: You must purchase Mistral AI with IBM separately before you are entitled to use this model.
mistral-large-instruct-2411	Mistral AI	131,072	• classification • code • extraction • generation • retrieval-augmented generation • summarization • translation	• Model card • Blog post for Mistral Large 2
mistral-small-instruct	Mistral AI	32,768	• classification • code • extraction • generation • retrieval-augmented generation • summarization • translation	• Model card • Blog post for Mistral Small
mistral-small-3-1-24b-instruct-2503	Mistral AI	131,072	• classification • code • extraction • generation • retrieval-augmented generation • summarization • translation	• Model card • Blog post for Mistral Small 3
mistral-small-24b-instruct-2501	Mistral AI	32,768	• classification • code • extraction • generation • retrieval-augmented generation • summarization • translation	• Model card • Blog post for Mistral Small 3
mixtral-8x7b-instruct-v01	Mistral AI	32,768	• classification • code • extraction • generation • retrieval-augmented generation • summarization • translation	• Model card • Research paper
mt0-xxl-13b	BigScience	4,096	• classification • extraction • generation • question answering • summarization	• Model card • Research paper
pixtral-12b	Mistral AI	128,000	• classification • generation • retrieval-augmented generation • summarization	• Model card • Blog post for Pixtral 12B
pixtral-large-instruct-2411	Mistral AI	128,000	• classification • generation • retrieval-augmented generation • summarization	• Model card • Blog post for Pixtral Large Note: You must purchase Mistral AI with IBM separately before you are entitled to use this model.

Learn more

IBM foundation models
Third-party foundation models
For more information about the foundation models that IBM provides for embedding and reranking text, see Supported encoder models.

Parent topic: Gen AI solutions