(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | gcp |
Server ID | 1724003 |
Name | a4x-maxgpu-4g-metal |
Description | Accelerator Optimized: 4 NVIDIA GB300 GPU, 144 vCPUs, 960GB RAM |
Family | a4x |
Hw Virt | - |
Status | active |
Observed At | 2026-10-01T00:11:20.068530Z |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|
Processor
vCPUs | 144 |
CPU Allocation | Dedicated |
CPU Architecture | arm64 |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 960 GiB |
| GPU | |
|---|---|
GPU Count | 4 |
GPU Memory Min | 279 GiB |
GPU Memory Total | 1 TB |
GPU Manufacturer | NVIDIA |
GPU Family | Blackwell |
GPU Model | GB300 |
GPUs |
|
| STORAGE | |
|---|---|
Storage Size | 12885 GB |
Storage Type | nvme ssd |
Storages |
|
| NETWORK | |
|---|---|
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
Server Description
An accelerator-optimized bare-metal platform featuring four Blackwell GPUs and 144 arm64 cores for high-density parallel computing.
Google Cloud Platform a4x-maxgpu-4g-metal is an accelerator-optimized bare-metal server designed for high-performance computing and machine learning workloads. Powered by an arm64 CPU architecture, the instance features 144 dedicated vCPUs and 960.0 GB of system memory, yielding 6.67 GB of RAM per core. The primary computational power comes from four integrated NVIDIA Blackwell GB300 GPUs, which provide a total of 1116 GB of VRAM. There is no bundled local storage, requiring external storage solutions for data persistence. This server is structured for resource-intensive operations, making it highly suitable for large-scale AI model training, deep learning inference, and complex data science simulations.
Economics
Alternatives
Servers of the Same Family
| INSTANCE | vCPUs | MEMORY | GPUs |
|---|---|---|---|
| a4x-highgpu-4g | 140 | 884 GiB | 4 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|