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.
You can choose to deploy foundation models that are provided with watsonx.ai, tuned models, or custom foundation models that suits a specialized use case. To learn more about the various ways you can use to deploy models in watsonx.ai, see Foundation model deployment methods.
For more information about the foundation models provided with watsonx.ai for embedding and reranking text, see Supported encoder models.
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 work with the following types of provided 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
You can inference the following supported foundation models that are provided by IBM. The foundation models must be deployed in your cluster by an administrator to be available for use. All IBM models are instruction-tuned.
Note:
A view of all foundation models is available on the Resource hub.
Latest IBM foundation models
The following table lists the latest IBM foundation models in watsonx.ai for inferencing.
| Model name | Context window (input + output tokens) |
Supported tasks | More information |
|---|---|---|---|
| ibm-defense-4-0-small | 131,072 | • classification • extraction • generation • question answering • summarization • retrieval-augmented generation • function calling |
• IBM Defense Model |
| ibm-defense-4-0-micro | 131,072 | • classification • extraction • generation • question answering • summarization • retrieval-augmented generation • function calling |
• IBM Defense Model |
| granite-docling-258M | 8,192 | • extraction • generation • retrieval-augmented generation |
• Granite Docling documentation |
| granite-4-h-tiny | 131,072 | • classification • extraction • generation • question answering • summarization • retrieval-augmented generation • code • extraction • translation • function calling |
• Granite 4.0 documentation |
| granite-4-h-micro | 131,072 | • classification • extraction • generation • question answering • summarization • retrieval-augmented generation • code • extraction • translation • function calling • code |
• Granite 4.0 documentation |
| granite-4-h-small | 131,072 | • classification • extraction • generation • question answering • summarization • retrieval-augmented generation • code • extraction • translation • function calling • code |
• Granite 4.0 documentation |
| ibm-defense-3-3-8b-instruct | 128,000 | • classification • extraction • generation • question answering • summarization • retrieval-augmented generation • code • extraction • translation • function calling |
• IBM Defense Model |
| granite-vision-3-3-2b | 131,072 | • question answering • generation |
• Granite Vision documentation |
| granite-3-3-8b-instruct | 131,072 | • classification • extraction • generation • question answering • summarization • retrieval-augmented generation • code • extraction • translation • function calling |
• Granite models blog |
| granite-guardian-3-2-5b | 128,000 | • classification • extraction • generation • question answering • summarization |
• Granite Guardian documentation |
| Model name | Context length Minimum data points |
More information |
|---|---|---|
| granite-ttm-512-96-r2 |
512 | • Granite Time Series documentation • Research paper |
| granite-ttm-1024-96-r2 |
1,024 | • Granite Time Series documentation • Research paper |
| granite-ttm-1536-96-r2 |
1,536 | • Granite Time Series documentation • Research paper |
Legacy IBM foundation models
The following table lists the legacy IBM foundation models in watsonx.ai for inferencing. When a newer version of a foundation model is released, the existing foundation models are moved to the legacy state. You can still access these legacy models with the same level of support as the latest versions, but switching to the newer models is recommended.
| Model name | Context window (input + output tokens) |
Supported tasks | More information |
|---|---|---|---|
| granite-3-2-8b-instruct | 131,072 | • classification • extraction • generation • question answering • summarization • retrieval-augmented generation • code • extraction • translation • function calling |
• Website • Research paper |
| granite-3-2b-instruct | 4,096 | • classification • extraction • function calling • generation • question answering • summarization |
• Website • Research paper |
| granite-3-8b-instruct | 4,096 | • classification • extraction • function calling • generation • question answering • summarization |
• Website • Research paper |
| granite-guardian-3-2b | 8,192 | • classification • extraction • generation • question answering • summarization |
• Website |
| granite-guardian-3-8b | 8,192 | • classification • extraction • generation • question answering • summarization |
• Website |
| granite-20b-code-base-schema-linking | 8,192 | • code | • Research paper |
| granite-20b-code-base-sql-gen | 8,192 | • code | • Research paper |
| granite-8b-code-instruct | 128,000 | • code • classification • extraction • generation • question answering • summarization |
• Website • Research paper |
| granite-vision-3-2-2b | 131,072 | • question answering | • Website • Research paper |
| granite-13b-instruct-v2 |
8,192 | • classification • extraction • generation • question answering • summarization |
• Website • Research paper |
Third-party foundation models
You can inference the following supported third-party foundation models. An administrator must deploy the foundation models in your cluster before you can use these models.
Note:
A view of all foundation models is available on the Resource hub.
Latest third-party foundation models
The following table lists the supported foundation models that are provided by third parties.
| Model name | Provider | Context window (input + output tokens) |
Supported tasks | More information |
|---|---|---|---|---|
| ministral-14b-instruct-2512 | Mistral AI | 262,144 | • classification • extraction • generation • retrieval-augmented generation • summarization • translation • function calling • question answering |
Blog post for Ministral 3 |
| mistral-large-2512 | Mistral AI | 131,072 | • classification • code • extraction • generation • retrieval-augmented generation • summarization • translation • function calling |
• Blog post for Mistral Large 3 |
| devstral-medium-2512 |
Mistral AI | 256,000 | • code | • Blog post for Devstral 2 Note:
|
| devstral-small-2512 |
Mistral AI | 256,000 | • code | • Blog post for Devstral 2 |
| codestral-2508 |
Mistral AI | 256,000 | • code | • Blog post for Codestral 25.08 Note:
|
| devstral-medium-2507 |
Mistral AI | 128,000 | • code | • Blog post for Codestral 25.01 Note:
|
| mistral-medium-2508 | Mistral AI | 131,072 | • classification • code • extraction • generation • retrieval-augmented generation • summarization • translation |
• Blog post for Mistral Medium 3
Note:
|
| mistral-small-3-2-24b-instruct-2506 | Mistral AI | 131,072 | • classification • extraction • generation • question answering • retrieval-augmented generation • summarization • function calling • code • translation |
• Research paper |
| gpt-oss-20b | OpenAI | 131,072 | • classification • extraction • generation • question answering • retrieval-augmented generation • summarization • function calling • code • translation |
• OpenAI blog |
| gpt-oss-120b | OpenAI | 131,072 | • classification • extraction • question answering • retrieval-augmented generation • summarization • function calling • code • translation |
• OpenAI blog |
| voxtral-small-24b-2507 | Mistral AI | 32,000 | • classification • extraction • generation • question answering • retrieval-augmented generation • summarization • translation • function calling • audio understanding |
• Voxtral blog |
| llama-4-maverick-17b-128e-instruct-fp8 | Meta | 131,072 | • classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization • translation • function calling |
• Meta AI blog |
| llama-4-maverick-17b-128e-instruct-int4 | Meta | 131,072 | • classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization • translation • function calling |
• Meta AI blog |
| llama-4-scout-17b-16e-instruct-int4 | Meta | 131,072 | • classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization • translation • function calling |
• Meta AI blog |
| llama-3-3-70b-instruct |
Meta | 131,072 | • classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization |
• Meta AI blog • Meta AI docs |
| llama-3-2-11b-vision-instruct | Meta | 131,072 | • classification • code generation and conversion • extraction • function calling • generation • question answering • retrieval-augmented generation • summarization |
• 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 |
• 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 |
• Meta AI blog • Research paper |
| ministral-8b-instruct | Mistral AI | 128,000 | • classification • code • extraction • generation • retrieval-augmented generation • summarization • translation • question answering • function calling |
• Blog post for Ministral 8b Note:
|
| mistral-large-instruct-2411 |
Mistral AI | 131,072 | • classification • code • extraction • generation • retrieval-augmented generation • summarization • translation |
• Blog post for Mistral Large 2 |
| pixtral-large-instruct-2411 |
Mistral AI | 128,000 | • classification • generation • retrieval-augmented generation • summarization |
• Blog post for Pixtral Large Note:
|
| 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 |
• Research paper |
Legacy third-party foundation models
The following table lists the legacy third-party foundation models in watsonx.ai for inferencing. When a newer version of a foundation model is released, the existing foundation models are moved to the legacy state. You can still access these legacy models with the same level of support as the latest versions, but switching to the newer models is recommended.
| Model name | Provider | Context window (input + output tokens) |
Supported tasks | More information |
|---|---|---|---|---|
| mistral-medium-2505 | Mistral AI | 131,072 | • classification • code • extraction • generation • retrieval-augmented generation • summarization • translation |
• Blog post for Mistral Medium 3 |
| mistral-small-3-1-24b-instruct-2503 | Mistral AI | 131,072 | • classification • code • extraction • generation • retrieval-augmented generation • summarization • translation |
• Blog post for Mistral Small 3 |
| codestral-2501 |
Mistral AI | 256,000 | • code | • Blog post for Codestral 25.01 Note:
|
| llama-3-2-1b-instruct | Meta | 131,072 | • classification • code generation and conversion • extraction • function calling • generation • question answering • retrieval-augmented generation • summarization |
• 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 |
• Meta AI blog • Research paper |
| llama-3-1-8b-instruct | Meta | 131,072 | • classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization |
• Meta AI blog |
| llama-3-1-70b-instruct | Meta | 131,072 | • classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization |
• Meta AI blog |
| mistral-large | Mistral AI | 32,768 | • classification • code • extraction • generation • retrieval-augmented generation • summarization • translation |
• Blog post for Mistral Large 2 Note:
|
| pixtral-12b | Mistral AI | 128,000 | • classification • generation • retrieval-augmented generation • summarization |
• Blog post for Pixtral 12B |
| mistral-small-24b-instruct-2501 | Mistral AI | 32,768 | • classification • code • extraction • generation • retrieval-augmented generation • summarization • translation |
• Blog post for Mistral Small 3 |
| codestral-22b | Mistral AI | 32,768 | • code | • Blog post for Codestral |
| flan-t5-xl-3b | 4,096 | • classification • extraction • generation • question answering • retrieval-augmented generation • summarization |
• 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 |
• Research paper |
| llama-4-scout-17b-16e-instruct | Meta | 131,072 | • classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization • translation • function calling |
• Meta AI blog |
| llama-2-13b-chat | Meta | 4,096 | • classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization |
• Research paper |
| mistral-small-instruct | Mistral AI | 32,768 | • classification • code • extraction • generation • retrieval-augmented generation • summarization • translation |
• Blog post for Mistral Small |
| llama-3-405b-instruct | Meta | 16,384 | • classification • code • extraction • generation • question answering • retrieval-augmented generation • summarization |
• Meta AI blog |
| mixtral-8x7b-instruct-v01 | Mistral AI | 32,768 | • classification • code • extraction • generation • retrieval-augmented generation • summarization • translation |
• Research paper |