g7.24xlarge by Amazon Web Services
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | aws |
Name | g7.24xlarge |
Description | Graphics intensive Gen7 24xlarge |
Family | g7 |
Hw Virt | - |
Status | active |
Observed At | 2026-08-03T01:13:24.792138 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
Ohio (US) / us-east-2 | 1.4257 USD/h | 14.2566 USD/h |
Oregon (US) / us-west-2 | 3.2252 USD/h | 14.2566 USD/h |
Northern Virgina (US) / us-east-1 | 5.2558 USD/h | 14.2566 USD/h |
Processor
vCPUs | 96 |
Hypervisor | nitro |
CPU Allocation | Dedicated |
CPU Cores | 96 |
CPU Speed | 3.9 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | Intel |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 384 GiB |
| GPU | |
|---|---|
GPU Count | 4 |
GPU Memory Min | 32 GiB |
GPU Memory Total | 128 GiB |
GPU Manufacturer | NVIDIA |
GPU Model | RTX PRO 4500 |
GPUs |
|
| STORAGE | |
|---|---|
Storage Size | 3800 GB |
Storage Type | nvme ssd |
Storages |
|
| NETWORK | |
|---|---|
Network Speed Baseline | 350 Gbps |
Network Speed Max | 350 Gbps |
Network Storage Speed Baseline | 40 Gbps |
Network Storage Speed Max | 40 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
Server Description
A high-density GPU instance featuring four dedicated graphics processors, high-speed NVMe storage, and 350 Gbps network bandwidth for intensive workloads.
Amazon Web Services g7.24xlarge is a graphics-intensive instance built on the AWS Nitro hypervisor. It features 96 dedicated physical Intel x86_64 cores operating at 3.9 GHz, paired with 384.0 GB of system memory. The hardware configuration includes four bundled NVIDIA RTX PRO 4500 GPUs with a total of 128 GB of VRAM, alongside 3800 GB of local NVMe SSD storage. Network performance is supported by a baseline bandwidth of 350 Gbps. This instance provides a high-density resource profile suitable for demanding multi-GPU workloads, rendering, and data-intensive processing. The dedicated core allocation ensures consistent compute performance without hyperthreading overhead. It is optimized for graphics rendering, machine learning inference, and high-throughput data processing workloads.
Economics
Alternatives
Servers of the Same Family
| INSTANCE | vCPUs | MEMORY | GPUs |
|---|---|---|---|
| g7.2xlarge | 8 | 32 GiB | 1 |
| g7.4xlarge | 16 | 64 GiB | 1 |
| g7.8xlarge | 32 | 128 GiB | 1 |
| g7.12xlarge | 48 | 192 GiB | 2 |
| g7.48xlarge | 192 | 768 GiB | 8 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|