GCP Compute Instance

a3-edgegpu-8g

The a3-edgegpu-8g is a GPU-accelerated GCP Compute instance with 208 vCPUs and 1872 GB of memory, 8 H100 GPUs, powered by Intel. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $87.8325/hr in us-central1.

Price History

Pricing by Region

Region On-Demand Spot Reserved 1Y
us-central1$87.832$37.665$63.792
us-east4$87.832$26.801$61.103
us-west1$87.832$37.665$63.792
asia-south1$91.346$27.938$63.408
northamerica-northeast2$96.712$18.277$67.133
us-east5$98.926$27.556$68.439
us-west4$98.926$28.868$68.821
europe-west2$100.129$9.708$69.505
europe-west9$101.886$23.669$70.725
europe-west3$103.642$30.257$72.145
europe-west4$111.817$32.627$79.656
asia-northeast3$112.794$29.785$78.297
asia-southeast1$113.555$36.291$78.824
asia-northeast1$125.789$31.196$87.534

Frequently Asked Questions

What is the a3-edgegpu-8g?
The a3-edgegpu-8g is a GPU-accelerated GCP Compute instance with 208 vCPUs and 1872 GB of memory, 8 H100 GPUs, powered by Intel. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $87.8325/hr in us-central1.
What is the cheapest region for a3-edgegpu-8g?
us-central1 at $87.832/hr on-demand.
How much does a3-edgegpu-8g cost per month?
Starting at $64117.70/mo on-demand in us-central1, or $7086.56/mo with spot pricing.

Run a free assessment to identify overprovisioned workloads, idle capacity, and your potential savings, in minutes.

Most clusters are overprovisioned.
Let's prove yours is.