a4x-highgpu-4g by Google Cloud Platform
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | gcp |
Server ID | 1724001 |
Name | a4x-highgpu-4g |
Description | Accelerator Optimized: 4 NVIDIA GB200 GPU, 140 vCPUs, 884GB RAM |
Family | a4x |
Hw Virt | - |
Status | active |
Observed At | 2026-09-09T04:24:50.304628 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|
Processor
vCPUs | 140 |
CPU Allocation | Dedicated |
CPU Architecture | arm64 |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 884 GiB |
| GPU | |
|---|---|
GPU Count | 4 |
GPU Memory Total | 0 MiB |
GPU Model | GB200 |
GPUs |
| STORAGE | |
|---|---|
Storage Size | 0 GB |
Storages |
| NETWORK | |
|---|---|
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
Server Description
An accelerator-optimized instance featuring four integrated GPUs and dedicated arm64 processors for highly parallelized computing and machine learning workloads.
Google Cloud Platform a4x-highgpu-4g is an accelerator-optimized instance designed for parallel computing workloads. It features 140 dedicated arm64 vCPUs and 884.0 GB of system memory, providing 6.31 GB of RAM per core. Acceleration is driven by four integrated NVIDIA GB200 GPUs. The instance does not include local storage or complimentary public IPv4 addresses, meaning storage must be provisioned externally. The arm64 architecture requires compatible software builds. This hardware profile is structured for workloads such as machine learning model training, large-scale artificial intelligence inference, and complex data science computations that require dense GPU resources and substantial system memory.
Economics
Alternatives
Servers of the Same Family
| INSTANCE | vCPUs | MEMORY | GPUs |
|---|---|---|---|
| a4x-maxgpu-4g-metal | 144 | 960 GiB | 4 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|