The ml.g5.4xlarge is a aws sagemaker instance type featuring multiple vCPUs and optimized memory, commonly used for sagemaker workloads.
| Compute | Value |
| vCPUs | 16 |
| Memory | 64 GiB |
| Physical Processor | N/A |
| GPU | 1 |
| GPU Memory | 24 |
| Network | Value |
| Network Performance | N/A |
| Storage | Value |
| Storage | 1 x 600 NVMe SSD, 1 x 3800 NVMe SSD |
| Amazon | Value |
| Current Generation | Yes |
| Instance Type | ml.g5.4xlarge |
| Instance | vCPUs | Memory |
|---|---|---|
| ml.g5.4xlarge | 16 | 64 |
| ml.g5.8xlarge | 32 | 128 |
| ml.g5.48xlarge | 192 | 768 |