AI Center considerations

On top of the core service requirements that are part of full platform requirements, AI Center requires additional resources, depending on the models that you want to run or train. For more details about the required GPU hardware generations and compatible NVIDIA drivers, refer to Compatibility Matrix.

Note: The following table describes the additional resources AI Center needs.

In this table, Data Disk is needed on all server nodes. This is not needed on agent nodes.

Use	CPU	RAM (GB)	GPU	Disk (GB)
Minimum for serving (ML Skill, one replica)	0.6	2	0	20 GB on the rancher partition
Minimum for Training (Pipeline)	1	4	0	20 GB on the rancher partition Minimum 51 GB AI Center disk partition(recommended 105 GB)
DU model Serving (ML Skill, one replica)	1	4	0	20 GB on the rancher partition
DU model Training	2	24	Strongly recommended	20 GB on the rancher partition Minimum 51 GB Data Disk (recommended 105 GB)

Note: The following table describes the required resources for small and average AI Center implementations. Note that these numbers are general guidance.

In this table, Data Disk is needed on all server nodes. This is not needed on agent nodes.

Use	CPU	RAM (GB)	GPU	Disk (GB)
Small implementation: 3 models served 1 concurrent pipelines	4	32	0	80 GB on the rancher partition1 105 Data Disk 2
Average implementation: 5 models served 2 concurrent pipelines DU model training	8	52	Strongly recommended	160 GB on the rancher partition3 315 Data Disk 4

¹ (3 skills +1 pipeline) * 20 GB on the rancher partition = 80 GB on the rancher partition

² 1 pipeline * 105GB = 105 Data disk

³ (5 skills + 2 pipeline + 1 DU pipeline) * 20 GB on the rancher partition = 160 GB on the rancher partition

⁴ (2 pipeline + 1 DU pipeline) * 105GB = 315 Data disk