Regional availability for services and features on IBM Cloud

Last updated: Dec 12, 2024

IBM watsonx is deployed on the IBM Cloud multi-zone region network. The availability of services and features can vary across regional data centers.

View the regional availability for every service in the Services catalog.

Regional availability of the watsonx services

Watsonx.ai includes the watsonx.ai Studio and watsonx.ai Runtime services to provide foundation and machine learning model tools. Regional support for watsonx.governance is also listed.

The watsonx.ai Studio and watsonx.ai Runtime services are available in the following regional data centers:

Dallas (us-south), in Texas US
Frankfurt (eu-de), in Germany
London (eu-gb), in England
Tokyo (jp-tok), in Japan
Sydney (au-syd), in Australia

Regional availability of watsonx.governance

Table 1. Regional deployments by service for watsonx.governance
	DAL	FRA	LON	TOK	SYD
watsonx.governance	✓	✓			✓

Regional availability of foundation models

The following table shows the IBM Cloud data centers where you can inference the foundation models that are curated by IBM. A checkmark indicates that the model is hosted in the region.

Table 1a. IBM Cloud data center support for inferencing foundation models provided by IBM
Model name	Dallas	Frankfurt	London	Sydney	Tokyo
allam-1-13b-instruct		✓
codellama-34b-instruct-hf	✓	✓	✓		✓
elyza-japanese-llama-2-7b-instruct					✓
flan-t5-xl-3b	✓	✓	✓		✓
flan-t5-xxl-11b	✓	✓	✓		✓
flan-ul2-20b	✓	✓	✓		✓
granite-13b-chat-v2	✓	✓	✓		✓
granite-13b-instruct-v2	✓	✓	✓	✓	✓
granite-7b-lab	✓	✓	✓		✓
granite-8b-japanese					✓
granite-20b-multilingual	✓	✓	✓	✓	✓
granite-3-2b-instruct	✓	✓	✓	✓	✓
granite-3-8b-instruct	✓	✓	✓	✓	✓
granite-guardian-3-2b	✓			✓
granite-guardian-3-8b	✓			✓
granite-3b-code-instruct	✓
granite-8b-code-instruct	✓			✓
granite-20b-code-instruct	✓	✓
granite-34b-code-instruct	✓
jais-13b-chat		✓
llama-3-3-70b-instruct	✓	✓
llama-3-2-1b-instruct	✓
llama-3-2-3b-instruct	✓
llama-3-2-11b-vision-instruct	✓	✓	✓	✓
llama-3-2-90b-vision-instruct	✓			✓
llama-guard-3-11b-vision	✓	✓	✓	✓
llama-3-1-8b-instruct	✓	✓	✓		✓
llama-3-1-70b-instruct	✓	✓	✓	✓	✓
llama-3-405b-instruct	✓
llama-3-8b-instruct	✓	✓	✓		✓
llama-3-70b-instruct	✓	✓	✓	✓	✓
llama-2-13b-chat	✓	✓	✓		✓
mistral-large	✓	✓	✓	✓
mixtral-8x7b-instruct-v01	✓	✓	✓		✓
pixtral-12b		✓	✓

For information about additional models that you can deploy on demand in Dallas, see Supported foundation models.

Regional availability of custom foundation models and deploy on demand models

The following table shows the IBM Cloud data centers where custom foundation models and deploy on demand models are supported. A checkmark indicates that you can upload and deploy your own foundational models or deploy an on demand model in the region.

Table 1b. IBM Cloud data center support for custom foundation model and deploy on demand model inferencing
Dallas	Frankfurt	London	Sydney	Tokyo
✓

Regional availability of foundation model tuning

The following table shows the IBM Cloud data centers where tuning the foundation model is supported. A checkmark indicates that you can use the Tuning Studio to tune the foundation model in the region.

Table 1c. IBM Cloud data center support for foundation model tuning
Model name	Dallas	Frankfurt	London	Sydney	Tokyo
flan-t5-xl-3b	✓	✓	✓		✓
granite-13b-instruct-v2	✓	✓	✓	✓	✓

Regional availability of encoder-only models

The following table shows the IBM Cloud data centers where embedding models and reranker models are available. A checkmark indicates that you can use the model in the region.

Table 1d. IBM Cloud data center support for encoder-only models
Model	Dallas	Frankfurt	London	Sydney	Tokyo
all-minilm-l6-v2	✓	✓	✓		✓
all-minilm-l12-v2	✓	✓	✓	✓	✓
ms-marco-minilm-l-12-v2	✓	✓	✓	✓	✓
multilingual-e5-large	✓	✓	✓	✓	✓
slate.125m.english.rtrvr-v2	✓	✓	✓	✓	✓
slate.125m.english.rtrvr	✓	✓	✓		✓
slate.30m.english.rtrvr-v2	✓	✓	✓	✓	✓
slate.30m.english.rtrvr	✓	✓	✓		✓

Tool and environment limitations for the Frankfurt region

Table 2. Frankfurt regional limitations
Service	Limitation
watsonx.ai Studio	If you need a Spark runtime, you must use the Spark environment in watsonx.ai Studio for the notebook editor tools.
watsonx.governance	Only one instance per region is supported.

Tool and environment limitations for the London region

Table 3. London regional limitations
Service	Limitation
watsonx.ai Studio	If you need a Spark runtime, you must use the Spark environment in watsonx.ai Studio for the notebook editor tools.
watsonx.ai Studio	IBM Orchestration Pipelines is not available.

Tool and environment limitations for the Sydney region

Table 4. Sydney regional limitations
Service	Limitation
watsonx.ai Studio	If you need a Spark runtime, you must use the Spark environment in watsonx.ai Studio for the notebook editor tools.
Decision Optimization	If you use the watsonx.ai Runtime API to run Decision Optimization jobs, you must first create a User API key.
watsonx.governance	No support for integration with Governance console
watsonx.governance	Only one instance per region is supported.

Tool and environment limitations for the Tokyo region

Table 5. Tokyo regional limitations
Service	Limitation
watsonx.ai Studio	If you need a Spark runtime, you must use the Spark environment in watsonx.ai Studio for the notebook editor tools.
watsonx.ai Studio	Multibyte characters are not supported in user-input fields in Data Refinery. Some fields allow multibyte characters but do not display them correctly.
watsonx.ai Studio	IBM Orchestration Pipelines is not available.

Regional availability of the Cloud Object Storage service

The region for the Cloud Object Storage service is Global. Cloud Object Storage buckets for workspaces are Regional buckets. For more information, see IBM Cloud docs: Cloud Object Storage endpoints and storage locations.

Learn more

Parent topic: Services and integrations