dl2q.24xlarge vs x8i.24xlarge
| dl2q.24xlarge | x8i.24xlarge |
| Machine Learning ASIC | Memory optimized |
| Deep learning / Machine Learning (ML) inference and training dl – Deep Learning 2 – Generation q – Qualcomm inference accelerator 24xlarge – Size | In-memory databases (like SAP HANA), big data engines (such as Apache Spark, Presto), high-performance computing (HPC), and memory-heavy enterprise apps. x – Extreme RAM / memory intensive 8 – Generation i – Intel processor 24xlarge – Size |
| 96 | 96 |
| 768 GiB | 1536 GiB |
| n/a | x86_64 |
| Intel Xeon Platinum 8259 (Cascade Lake) | Intel Xeon Scalable (Granite Rapids) |
| 3.9 GHz | |
| 0 | 2 |
| no | no |
| 8 | |
| no | no |
| 128 GiB | |
| no | no |
| dl2q.24xlarge | x8i.12xlarge, x8i.16xlarge, x8i.24xlarge, x8i.2xlarge, x8i.32xlarge, x8i.48xlarge, x8i.4xlarge, x8i.64xlarge, x8i.8xlarge, x8i.96xlarge, x8i.large, x8i.metal-48xl, x8i.metal-96xl, x8i.xlarge |
| x8aedz.24xlarge, x8g.24xlarge | |
| no | no |
| no | no |
| no | no |
| EBS only | EBS only |
| default | |
| supported | |
| required | |
| 19000 MBps | 30000 MBps |
| 30000 Mbps | |
| 3750 Mbps | |
| 120000 IOPS | |
| 120000 IOPS | |
| 30000 Mbps | |
| 3750 Mbps | |
| 100 Gigabit | 40000 Megabit |
| yes | yes |
| 16 | |
| 1 | |
| 64 | |
| 64 | |
| no | yes |
| required | |
| no | no |
| no | yes |
| no | yes |
| 1.00x | 1.13x |
Regional Prices
Geography | Region | dl2q.24xlarge | x8i.24xlarge |
|---|---|---|---|
| Europe | Europe (Frankfurt) (eu-central-1) | 11.5952 | n/a |
| Hidden | Hidden (hidden-1) | n/a | 11.9789 |
| Hidden | Hidden (hidden-2) | n/a | 14.7058 |
| US | US East (Ohio) (us-east-2) | n/a | 10.5038 |
| US | US East (Virginia) (us-east-1) | n/a | 10.5038 |
| US | US West (Oregon) (us-west-2) | 8.9194 | 10.5038 |