Compare GCP Instances

Instance Typen4a-highcpu-8a3-megagpu-8g
DetailsHigh-performance web servers, scientific modeling, batch processing, distributed analytics, HPC, machine/deep learning inference, ad serving, scalable multiplayer gaming, and video encoding.

n – General purpose
4 – Generation
highcpu – 1-2x RAM/CPU ratio
8 – Number of CPUs
Optimized for accelerated high performance computing workloads.

a – Accelerator optimized
3 – Generation
megagpu – Large amound of GPU memory - 80x RAM/GPU ratio
8g – Number of GPUs
Instance FamilyGeneral-purposeAccelerator optimized
Description8 vCPUs, 16 GB RAMAccelerator Optimized: 8 NVIDIA H100 GPU, 208 vCPUs, 1872GB RAM, 16 local SSD
vCPUs8208
Memory16 GiB1872 GiB
CPU Architecturearm64x86_64
ProcessorGoogle AxionIntel Sapphire Rapids
Shared CPUnono
GPUnoyes
GPUs8
GPU Namenvidia-h100-mega-80gb
GPU Total RAM (GiB)640
Sustained Discounts (SUDs)nono
Extended Memoryyes
Sole Tenancyyesyes
Nested Virtualizationnono
Custom Shapesyesno
Confidential Computenono
Maximum Persistent Disks16128
Maximum Persistent Disks Size263168 GB524288 GB
Disk Interface TypeNVMeNVMe
Local SSDnoyes
Max Local SSD6000 GB
Extreme Persistent Disksnono
Hyperdisk Extremenoyes
Hyperdisk Throughputyesyes
Network InterfacesgVNICgVNIC
Avg Price Diff1.00x379.25x

Regional Prices

US Dollar ($)
Per Hour
On Demand
Geography
Region
n4a-highcpu-8
a3-megagpu-8g
HiddenHidden (hidden-1)0.2598101.5371
HiddenHidden (hidden-2)0.2728103.8609
HiddenHidden (hidden-3)0.2861108.8129
HiddenHidden (hidden-4)0.2962115.2678
HiddenHidden (hidden-5)0.3066117.5135
HiddenHidden (hidden-6)0.3205118.4216
HiddenHidden (hidden-7)n/a119.2514
North AmericaIowa (us-central1)0.2598n/a
North AmericaOhio (us-east5)n/a93.4091
North AmericaOregon (us-west1)n/a92.2143
North AmericaSouth Carolina (us-east1)0.2598n/a
North AmericaVirginia (us-east4)0.259892.2143
Activate subscription to see all regions and unlock all features