Compare GCP Instances

Instance Typea2-ultragpu-8ga2-megagpu-16g
DetailsOptimized for accelerated high performance computing workloads.

a – Accelerator optimized
2 – Generation
ultragpu – Extra large amound of GPU memory
8g – Number of GPUs
Optimized for accelerated high performance computing workloads.

a – Accelerator optimized
2 – Generation
megagpu – Large amound of GPU memory - 80x RAM/GPU ratio
16g – Number of GPUs
Instance FamilyAccelerator optimizedAccelerator optimized
DescriptionAccelerator Optimized: 8 NVIDIA A100 80GB GPUs, 96 vCPUs, 1360GB RAM, 8 local SSDAccelerator Optimized: 16 NVIDIA Tesla A100 GPUs, 96 vCPUs, 1360GB RAM
vCPUs9696
Memory1360 GiB1360 GiB
CPU Architecturex86_64x86_64
ProcessorIntel Cascade LakeIntel Cascade Lake
Coremark Score1258852
Shared CPUnono
GPUyesyes
GPUs816
GPU Namenvidia-a100-80gbnvidia-tesla-a100
GPU Total RAM (GiB)640640
Sustained Discounts (SUDs)nono
Sole Tenancyyesyes
Nested Virtualizationyesyes
Custom Shapesnono
Confidential Computenono
Maximum Persistent Disks128128
Maximum Persistent Disks Size524288 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 Diff1.00x1.25x

Regional Prices

US Dollar ($)
Per Hour
On Demand
Geography
Region
a2-ultragpu-8g
a2-megagpu-16g
North AmericaIowa (us-central1)n/a55.7395
North AmericaOhio (us-east5)44.1906n/a
APACSingapore (asia-southeast1)49.619860.4762
North AmericaVirginia (us-east4)45.3002n/a
Activate subscription to see all regions and unlock all features  

Related Comparisons

Other generations of these machines worth weighing up.