Compare GCP Instances

Instance Typea2-ultragpu-2ga2-highgpu-4g
DetailsOptimized for accelerated high performance computing workloads.

a – Accelerator optimized
2 – Generation
ultragpu – Extra large amound of GPU memory
2g – Number of GPUs
Optimized for accelerated high performance computing workloads.

a – Accelerator optimized
2 – Generation
highgpu – High amound of GPU memory - 40x RAM/GPU ratio
4g – Number of GPUs
Instance FamilyAccelerator optimizedAccelerator optimized
DescriptionAccelerator Optimized: 2 NVIDIA A100 80GB GPUs, 24 vCPUs, 340GB RAM, 2 local SSDAccelerator Optimized: 4 NVIDIA Tesla A100 GPUs, 48 vCPUs, 340GB RAM
vCPUs2448
Memory340 GiB340 GiB
CPU Architecturex86_64x86_64
ProcessorIntel Cascade LakeIntel Cascade Lake
Shared CPUnono
GPUyesyes
GPUs24
GPU Namenvidia-a100-80gbnvidia-tesla-a100
GPU Total RAM (GiB)160160
Sustained Discounts (SUDs)nono
Sole Tenancyyesyes
Nested Virtualizationyesyes
Custom Shapesnono
Confidential Computenono
Maximum Persistent Disks128128
Maximum Persistent Disks Size263168 GB524288 GB
Disk Interface TypeSCSI (PD, Local SSD) NVMe (Local SSD)SCSI (PD, Local SSD) NVMe (Local SSD)
Local SSDyesyes
Max Local SSD3000 GB3000 GB
Extreme Persistent Disksnono
Hyperdisk Extremenono
Hyperdisk Throughputnono
Network InterfacesgVNIC, VirtIO-NetgVNIC, VirtIO-Net
Avg Price Diff1.00x1.36x

Regional Prices

US Dollar ($)
Per Hour
On Demand
Geography
Region
a2-ultragpu-2g
a2-highgpu-4g
HiddenHidden (hidden-1)n/a15.7374
HiddenHidden (hidden-2)n/a16.0550
HiddenHidden (hidden-3)n/a16.1629
HiddenHidden (hidden-4)n/a16.1984
HiddenHidden (hidden-5)n/a16.1984
HiddenHidden (hidden-6)n/a17.3003
North AmericaIowa (us-central1)n/a14.6935
North AmericaOhio (us-east5)11.0476n/a
North AmericaOregon (us-west1)n/a14.6935
APACSingapore (asia-southeast1)12.4050n/a
North AmericaSouth Carolina (us-east1)n/a14.6935
North AmericaVirginia (us-east4)11.3251n/a
Activate subscription to see all regions and unlock all features  

Related Comparisons

Other generations of these machines worth weighing up.