Supported foundation models

IBM watsonx Orchestrate supports a diverse range of AI models for the capabilities within the product. For each model listed, you can learn more about their details so you can choose the model that fits your business needs.

Each model contains the reference for its Model card where you can get more information about technical specifications of the model.

General considerations

Builders can update the parameters of the model to change the amount of tokens that the output of the model must return in Generative AI skills in Skill studio.

Find information such as the supported languages, latest updates, and trainning data for the models available in their model card.

Foundation model lifecycle

The IBM watsonx Orchestrate product is evolving continuously and as technology improves, some foundation models get deprecated or withdrawn from support. See the following table for more details on deprecated or withdrawn models.

Model name Deprecated Withdrawn Next recommended model
ibm/granite-13b-chat-v2 November 2024 From 19 January 2025 ibm/granite-3-8b-instruct
meta-llama/llama-3-70b-instruct November 2024 From 19 January 2025 meta-llama/llama-3-1-70b-instruct
meta-llama/llama-3-8b-instruct November 2024 From 19 January 2025 meta-llama/llama-3-1-8b-instruct

Indicates the foundation model is deprecated. You can continue using the deprecated foundation model. However, you might receive a notification in the UI about the upcoming model removal.

Indicates that the support to a foundation model is withdrawn and the product moves you to the most recent version of the same model family.

granite-13b-chat-v2

The Granite 13 Billion chat V2 (granite-13b-chat-v2) model is the chat-focused variant initialized from the pre-trained Granite Base 13 Billion Base V2 (granite-13b-base-v2) model. granite-13b-base-v2 has been trained using over 2.5T tokens. IBM Generative AI Large Language Foundation Models are Enterprise-level English-language models trained with a large volume of data that has been subjected to intensive pre-processing and careful analysis.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Extraction

Components that use this model:

Model card: ibm/granite-13b-chat-v2

granite-20b-multilingual

IBM Generative AI Large Language Foundation Models are Enterprise-level language models trained with a large volume of data that has been subjected to intensive pre-processing and careful analysis. The Granite 20 Billion Multilingual (granite-20b-multilingual) model has been trained using over 2.6 trillion tokens and further fine-tuned using a collection of instruction-tuning datasets. The model underwent extended pre-training using multilingual common crawl data resulting in a model that works with English, German, Spanish, French, and Portuguese.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Extraction

Components that use this model:

Model card: ibm/granite-20b-multilingual

granite-13b-instruct-v2

IBM Generative AI Large Language Foundation Models are Enterprise-level English-language models trained with a large volume of data that has been subjected to intensive pre-processing and careful analysis. The Granite 13 Billion Instruct V2.0 (granite.13b.instruct.v2) model is the instruction-tuned variant initialized from the pre-trained Granite Base 13 Billion Base V2.0 (granite.13b.base.v2) model. granite.13b.base.v2 has been trained using over 2.5T tokens. The Granite family of models support all 5 language tasks (Q&A, Generate, Extract, Summarize, and Classify).

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Extraction

Components that use this model:

Model card: ibm/granite-13b-instruct-v2

granite-3-8b-instruct

Granite-3.0-8B-Instruct is a 8B parameter model finetuned from Granite-3.0-8B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. The model is designed to respond to general instructions and can be used to build AI assistants for multiple domains, including business applications.

Usage:

  • Question answering
  • Summarization
  • Classification
  • Generation
  • Extraction
  • Function calling

Components that use this model:

Model card: ibm/granite-3-8b-instruct

granite-3-2b-instruct

Granite-3.0-2B-Instruct is a lightweight and open-source 2B parameter model fine tuned from Granite-3.0-2B-Base on a combination of open-source and proprietary instruction data with a permissively licensed. The model is designed to respond to general instructions and can be used to build AI assistants for multiple domains, including business applications.

Usage:

  • Question answering
  • Summarization
  • Classification
  • Generation
  • Extraction
  • Function calling

Components that use this model:

Model card: ibm/granite-3-2b-instruct

llama-2-13b-chat

Meta developed and released the Llama 2 family of large language models (LLMs), a collection of pre-trained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. The fine-tuned LLMs called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks that were tested, and in the human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction

Components that use this model:

Model card: meta-llama/llama-2-13b-chat

llama-3-1-70b-instruct

The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pre-trained and instruction tuned generative models. Instruction tuned text only models are intended for assistant-like chat, whereas pre-trained models can be adapted for a variety of natural language generation tasks. The Llama 3.1 model collection also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction
  • Function calling

Components that use this model:

Model card: meta-llama/llama-3-1-70b-instruct

llama-3-1-8b-instruct

The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models. Instruction tuned text only models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. The Llama 3.1 model collection also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction
  • Function calling

Components that use this model:

Model card: meta-llama/llama-3-1-8b-instruct

llama-3-405b-instruct

Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction
  • Function calling

Components that use this model:

Model card: meta-llama/llama-3-405b-instruct

llama-3-70b-instruct

Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction

Components that use this model:

Model card: meta-llama/llama-3-70b-instruct

llama-3-8b-instruct

Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction

Components that use this model:

Model card: meta-llama/llama-3-8b-instruct

llama-3-2-1b-instruct

The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in or text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open sources and closed chat models on common industry benchmarks.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction
  • Function calling

Components that use this model:

Model card: meta-llama/llama-3-2-1b-instruct

llama-3-2-3b-instruct

The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open sources and closed chat models on common industry benchmarks.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction
  • Function calling

Components that use this model:

Model card: meta-llama/llama-3-2-3b-instruct

llama-3-2-11b-vision-instruct

The Llama 3.2-Vision collection of multi-modal large language models (LLMs) is a collection of pre-trained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text + images in / text out). The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. The models outperform many of the available open sources and closed multi-modal models on common industry benchmarks.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction
  • Function calling

Components that use this model:

Model card: meta-llama/llama-3-2-11b-vision-instruct

llama-3-2-90b-vision-instruct

The Llama 3.2-Vision collection of multi-modal large language models (LLMs) is a collection of pre-trained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text + images in / text out). The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. The models outperform many of the available open sources and closed multi-modal models on common industry benchmarks.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction
  • Function calling

Components that use this model:

Model card: meta-llama/llama-3-2-90b-vision-instruct

llama-3-3-70b-instruct

Llama 3.3 is intended for commercial and research use in multiple languages. Instruction tuned text-only models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.

Usage:

  • Question answering
  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction
  • Function calling

Components that use this model:

Model card: meta-llama/llama-3-3-70B-instruct

mistral-large

Mistral Large 2 is a cutting-edge Large Language Model (LLM) that excels in reasoning, knowledge, and coding domains.

Usage:

  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction
  • Function calling

Components that use this model:

Model card: mistralai/mistral-large

mixtral-8x7b-instruct-v01

The Mixtral-8x7B Large Language Model (LLM) is a pre-trained generative Sparse Mixture of Experts.

Usage:

  • Summarization
  • Retrieval-Augmented Generation
  • Classification
  • Generation
  • Code generation and conversion
  • Extraction

Components that use this model:

Model card: mistralai/mixtral-8x7b-instruct-v01


Parent topic:

Reference