Apply for NVIDIA NeMo LLM service early access.

NeMo LLM service provides the fastest path to customize and use foundation large language models (LLMs) and deploy on private and public clouds.

Access to NeMo LLM service is currently in private beta.

The NVIDIA NeMo LLM Service Early Access program provides the following functionalities in EA:

  • A playground to use and experiment with large language models, such as the Megatron 530B model.
  • Ability to customize a pre-trained large language model using p-tuning techniques for a domain-specific use-case or task.
  • Ability to deploy large language models on-prem or cloud, or experiment via the Playground, or utilize NVIDIA’s managed API service.

To participate, please fill out the short application and provide details about your use case. You must be a member of the NVIDIA developer program and logged in with your organization's email address. We will not approve early access applications from personal email accounts.

After approval, we will require an NDA before granting access.