Compare GCP Instances

Instance Typet2a-standard-8a2-highgpu-8g
DetailsTau T-instances where each vCPU is equivalent to an entire core that gives cost-effective performance. Scale-out workloads, Web servers, Containerized microservices.

t – General purpose with entire core
2 – Generation
standard – 4x RAM/CPU ratio
8 – Number of CPUs
Optimized for accelerated high performance computing workloads.

a – Accelerator optimized
2 – Generation
highgpu – High amound of GPU memory - 40x RAM/GPU ratio
8g – Number of GPUs
Instance FamilyGeneral-purposeAccelerator optimized
Description8 vCPUs, 32 GB RAMAccelerator Optimized: 8 NVIDIA Tesla A100 GPUs, 96 vCPUs, 680GB RAM
vCPUs896
Memory32 GiB680 GiB
CPU Architecturearm64x86_64
ProcessorAmpere AltraIntel Cascade Lake
Coremark Score1882061269327
Shared CPUnono
GPUnoyes
GPUs8
GPU Namenvidia-tesla-a100
GPU Total RAM (GiB)320
Sustained Discounts (SUDs)nono
25%-50% Usage Sustained Discount0.8
50%-75% Usage Sustained Discount0.6
75%-100% Usage Sustained Discount0.4
Sole Tenancynoyes
Nested Virtualizationnoyes
Custom Shapesnono
Confidential Computenono
Maximum Persistent Disks128128
Maximum Persistent Disks Size263168 GB524288 GB
Disk Interface TypeNVMeSCSI (PD, Local SSD) NVMe (Local SSD)
Local SSDnoyes
Max Local SSD3000 GB
Extreme Persistent Disksnono
Hyperdisk Extremenono
Hyperdisk Throughputnono
Network InterfacesgVNICgVNIC, VirtIO-Net
Avg Price Diff1.00x93.42x

Regional Prices

US Dollar ($)
Per Hour
On Demand
Geography
Region
t2a-standard-8
a2-highgpu-8g
HiddenHidden (hidden-1)n/a31.4748
HiddenHidden (hidden-2)n/a32.1101
HiddenHidden (hidden-3)n/a32.3258
HiddenHidden (hidden-4)n/a32.3967
HiddenHidden (hidden-5)n/a32.3967
HiddenHidden (hidden-6)n/a34.6005
North AmericaIowa (us-central1)0.308029.3871
EuropeNetherlands (europe-west4)0.3236n/a
North AmericaOregon (us-west1)n/a29.3871
APACSingapore (asia-southeast1)0.3798n/a
North AmericaSouth Carolina (us-east1)n/a29.3871
Activate subscription to see all regions and unlock all features