trn2.48xlarge by Amazon Web Services
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | aws |
Name | trn2.48xlarge |
Description | AWS Trainium Gen2 48xlarge |
Family | Accelerated Computing |
Series | trn2 |
Hw Virt | - |
Status | active |
Observed At | 2026-11-11T22:18:05.961905 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
Ohio (US) / us-east-2 | 8.686167 USD/h | - |
Oregon (US) / us-west-2 | 15.7601 USD/h | - |
Quebec (CA) / ca-central-1 | 20.0991 USD/h | - |
Tokyo (JP) / ap-northeast-1 | 26.2756 USD/h | - |
Mumbai (IN) / ap-south-1 | 32.9759 USD/h | - |
Hyderabad (IN) / ap-south-2 | 10.3157 USD/h | 103.157 USD/h |
Processor
vCPUs | 192 |
Hypervisor | nitro |
CPU Allocation | Dedicated |
CPU Cores | 96 |
CPU Speed | 3.5 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | Intel |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 2 TB |
| ACCELERATORS | |
|---|---|
Accelerator Count | 0 |
Accelerator Memory Min | 0 MiB |
Accelerator Memory Total | 0 MiB |
Accelerators |
| STORAGE | |
|---|---|
Storage Size | 7600 GB |
Storage Type | nvme ssd |
Storages |
|
Compatible Storage IDs | standard, gp2, gp3, st1, sc1, io1, io2 |
| NETWORK | |
|---|---|
Network Speed Baseline | 3200 Gbps |
Network Speed Max | 3200 Gbps |
Network Storage Speed Baseline | 80 Gbps |
Network Storage Speed Max | 80 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
Server Description
High-density cloud server featuring 192 dedicated Intel vCPUs, 2 TB of system memory, 7.6 TB NVMe storage, and 200 Gbps network bandwidth.
Amazon Web Services trn2.48xlarge is a high-capacity cloud instance built on the AWS Nitro hypervisor platform. It features an Intel x86_64 processor delivering 96 physical cores and 192 dedicated vCPUs at a clock speed of 3.5 GHz. The server is equipped with 2048.0 GB of memory, corresponding to 10.67 GB per core, along with 7600 GB of local NVMe SSD storage for intensive disk I/O demands. High-speed networking is supported via a 200 Gbps baseline network bandwidth. Without integrated GPUs, the instance relies on its massive system memory, dedicated CPU allocation, and high network throughput to execute memory-intensive and data-heavy operations efficiently. The hardware combination offers high resource density on a single node, making it well suited for large database deployments, big data analytics, in-memory caching, and demanding enterprise computation tasks requiring substantial memory footprints.
Economics
Alternatives
Servers of the Same Family
| INSTANCE | vCPUs | MEMORY | Accelerators |
|---|---|---|---|
| g6f.large | 2 | 8 GiB | ⅛ |
| inf1.xlarge | 4 | 8 GiB | 0 |
| inf2.xlarge | 4 | 16 GiB | 0 |
| g6f.xlarge | 4 | 16 GiB | ⅛ |
| g5g.xlarge | 4 | 8 GiB | 1 |
| g4dn.xlarge | 4 | 16 GiB | 1 |
| g5.xlarge | 4 | 16 GiB | 1 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | Accelerators |
|---|