trn1.2xlarge vs g7e.2xlarge
| trn1.2xlarge | g7e.2xlarge |
| Machine Learning ASIC | GPU instance |
| Machine Learning (ML) training trn – AWS Trainium 1 – Generation 2xlarge – Size | Machine Learning (ML), 3D visualizations, graphics-heavy remote workstations, 3D rendering, application streaming, video encoding, and server-side graphics tasks. g – GPU (Graphics Processing Unit) 7 – Generation e – Extra storage or memory 2xlarge – Size |
| 8 | 8 |
| 32 GiB | 64 GiB |
| x86_64 | x86_64 |
| Intel Xeon Scalable (Icelake) | Intel Xeon Scalable (Emerald Rapids) |
| 3.5 GHz | 2.4 GHz |
| 2 | 2 |
| no | yes |
| RTX PRO Server 6000 | |
| NVIDIA | |
| 1 | 1 |
| 96 GiB | |
| 96 GiB | |
| no | no |
| 32 GiB | 96 GiB |
| no | no |
| trn1.2xlarge, trn1.32xlarge | g7e.12xlarge, g7e.24xlarge, g7e.2xlarge, g7e.48xlarge, g7e.4xlarge, g7e.8xlarge |
| g6e.2xlarge, g7e.2xlarge | |
| ml.trn1.2xlarge | ml.g7e.2xlarge |
| no | no |
| no | no |
| no | no |
| 1 x 475 NVMe SSD | 1 x 1900 NVMe SSD |
| default | default |
| supported | supported |
| required | required |
| up to 20480 MBps | up to 5000 MBps |
| 5000 Mbps | 2000 Mbps |
| 625 Mbps | 250 Mbps |
| 16250 IOPS | 8000 IOPS |
| 65000 IOPS | 20000 IOPS |
| 20000 Mbps | 5000 Mbps |
| 2500 Mbps | 625 Mbps |
| 12500 Megabit | 50 Gigabit |
| yes | yes |
| 4 | 4 |
| 1 | 1 |
| 15 | 64 |
| 15 | 64 |
| yes | yes |
| required | required |
| no | no |
| yes | yes |
| no | no |
| 1.00x | 3.03x |
Regional Prices
Geography | Region | trn1.2xlarge | g7e.2xlarge |
|---|---|---|---|
| Hidden | Hidden (hidden-1) | n/a | 3.5438 |
| Hidden | Hidden (hidden-2) | n/a | 4.1348 |
| Hidden | Hidden (hidden-3) | n/a | 4.8775 |
| Hidden | Hidden (hidden-4) | n/a | 5.8453 |
| US | US East (Ohio) (us-east-2) | 1.3438 | 3.3631 |
| US | US East (Virginia) (us-east-1) | 1.3438 | 3.3631 |
| US | US West (Oregon) (us-west-2) | 1.3438 | 3.3631 |