Compare GCP Instances
| a2-highgpu-4g | a2-ultragpu-4g |
| 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 | Optimized for accelerated high performance computing workloads. a – Accelerator optimized 2 – Generation ultragpu – Extra large amound of GPU memory 4g – Number of GPUs |
| Accelerator optimized | Accelerator optimized |
| Accelerator Optimized: 4 NVIDIA Tesla A100 GPUs, 48 vCPUs, 340GB RAM | Accelerator Optimized: 4 NVIDIA A100 80GB GPUs, 48 vCPUs, 680GB RAM, 4 local SSD |
| 48 | 48 |
| 340 GiB | 680 GiB |
| x86_64 | x86_64 |
| Intel Cascade Lake | Intel Cascade Lake |
| no | no |
| yes | yes |
| 4 | 4 |
| nvidia-tesla-a100 | nvidia-a100-80gb |
| 340 | 680 |
| no | no |
| yes | yes |
| yes | yes |
| no | no |
| no | no |
| 128 | 128 |
| 524288 GB | 524288 GB |
| SCSI (PD, Local SSD) NVMe (Local SSD) | SCSI (PD, Local SSD) NVMe (Local SSD) |
| yes | yes |
| 3000 GB | 3000 GB |
| no | no |
| no | no |
| no | no |
| gVNIC, VirtIO-Net | gVNIC, VirtIO-Net |
| 1.00x | 1.43x |
Regional Prices
Geography | Region | a2-highgpu-4g | a2-ultragpu-4g |
|---|---|---|---|
| Hidden | Hidden (hidden-1) | 14.9919 | 22.6501 |
| Hidden | Hidden (hidden-2) | 15.7374 | 24.8099 |
| Hidden | Hidden (hidden-3) | 16.0550 | n/a |
| Hidden | Hidden (hidden-4) | 16.1629 | n/a |
| Hidden | Hidden (hidden-5) | 16.1984 | n/a |
| Hidden | Hidden (hidden-6) | 16.1984 | n/a |
| Hidden | Hidden (hidden-7) | 17.3003 | n/a |
| North America | Iowa (us-central1) | 14.6935 | 20.1108 |
| Europe | Netherlands (europe-west4) | n/a | 22.1429 |
| North America | Ohio (us-east5) | n/a | 22.0953 |
| North America | Oregon (us-west1) | 14.6935 | n/a |
| North America | South Carolina (us-east1) | 14.6935 | n/a |