Instance Details
| Compute | Value |
|---|---|
| vCPUs | 8 |
| Memory (GiB) | 32 |
| Memory per vCPU (GiB) | 4 |
| Physical Processor | Intel Xeon Scalable (Icelake) |
| Clock Speed (GHz) | Up to 3.5 GHz |
| CPU Architecture | x86_64 |
| GPU | 1 |
| GPU Architecture | AWS Inferentia |
| Video Memory (GiB) | 32 |
| GPU Compute Capability (?) | 0 |
| FPGA | 0 |
| Networking | Value |
|---|---|
| Network Performance (Gibps) | up to 12.5 |
| Enhanced Networking | true |
| IPv6 | true |
| Placement Group (?) |
| Storage | Value |
|---|---|
| EBS Optimized | true |
| Max Bandwidth (Mbps) on (EBS) | 20000 |
| Max Throughput (MB/s) on (EBS) | 2500 |
| Max I/O operations/second (IOPS) | 65000 |
| Baseline Bandwidth (Mbps) on (EBS) | 5000 |
| Baseline Throughput (MB/s) on (EBS) | 625 |
| Baseline I/O operations/second (IOPS) | 16250 |
| Devices | 1 |
| Swap Partition | false |
| NVME Drive (?) | true |
| Disk Space (GiB) | 474 |
| SSD | true |
| Initialize Storage | false |
| Amazon | Value |
|---|---|
| Generation | current |
| Instance Type | trn1.2xlarge |
| Family | Machine Learning ASIC Instances |
| Name | TRN1 Double Extra Large |
| Elastic Map Reduce (EMR) | false |
