Compare GCP Instances

Instance Typea2-highgpu-8ga3-megagpu-8g
DetailsOptimized 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
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 FamilyAccelerator optimizedAccelerator optimized
DescriptionAccelerator Optimized: 8 NVIDIA Tesla A100 GPUs, 96 vCPUs, 680GB RAMAccelerator Optimized: 8 NVIDIA H100 GPU, 208 vCPUs, 1872GB RAM, 16 local SSD
vCPUs96208
Memory680 GiB1872 GiB
CPU Architecturex86_64x86_64
ProcessorIntel Cascade LakeIntel Sapphire Rapids
Coremark Score1269327
Shared CPUnono
GPUyesyes
GPUs88
GPU Namenvidia-tesla-a100nvidia-h100-mega-80gb
GPU Total RAM (GiB)320640
Sustained Discounts (SUDs)nono
Sole Tenancyyesyes
Nested Virtualizationyesno
Custom Shapesnono
Confidential Computenono
Maximum Persistent Disks128128
Maximum Persistent Disks Size524288 GB524288 GB
Disk Interface TypeSCSI (PD, Local SSD) NVMe (Local SSD)NVMe
Local SSDyesyes
Max Local SSD3000 GB6000 GB
Extreme Persistent Disksnono
Hyperdisk Extremenoyes
Hyperdisk Throughputnoyes
Network InterfacesgVNIC, VirtIO-NetgVNIC
Avg Price Diff1.00x3.37x

Regional Prices

US Dollar ($)
Per Hour
On Demand
Geography
Region
a2-highgpu-8g
a3-megagpu-8g
HiddenHidden (hidden-1)31.4748101.5371
HiddenHidden (hidden-2)32.1101103.8609
HiddenHidden (hidden-3)32.3258108.8129
HiddenHidden (hidden-4)32.3967115.2678
HiddenHidden (hidden-5)32.3967117.5135
HiddenHidden (hidden-6)34.6005118.4216
HiddenHidden (hidden-7)n/a119.2514
North AmericaIowa (us-central1)29.3871n/a
North AmericaOhio (us-east5)n/a93.4091
North AmericaOregon (us-west1)29.387192.2143
North AmericaSouth Carolina (us-east1)29.3871n/a
North AmericaVirginia (us-east4)n/a92.2143
Activate subscription to see all regions and unlock all features