Requesting 2 x NVIDIA A100, 4 x NVIDIA L40S GPU and/or 2 x NVIDIA H100 profiles. These would be aligned to llama-3-3-70b-instruct, presumably the most popular model available on watsonx.ai today.
watsonx.ai FM hardware reqs here: https://www.ibm.com/docs/en/software-hub/5.1.x?topic=install-foundation-models
| Idea priority | Urgent |
| Needed By | Yesterday (Let's go already!) |
By clicking the "Post Comment" or "Submit Idea" button, you are agreeing to the IBM Ideas Portal Terms of Use.
Do not place IBM confidential, company confidential, or personal information into any field.
2 A100 profiles already exists. Not sure why that is listed here.
We would not be doing 4 L40s profile, as 1 H200 profile would give what is asked here.
We plan to introduce granular profiles on H200 as part of fall plan 2026.