GCP - Veri Documentation

GCP offers genuine single-GPU A100 VMs — the main reason to pick it over AWS, where the big cards only come as whole 8-GPU nodes.

Serving shapes

`gpu_type`	Memory	GPUs per node
`A100-80GB`	80 GB	1

Single H100 VMs on GCP are Spot-only (preemptible), so they are not offered for serving. To serve on H100, use AWS.

Creating a deployment

client.deployments.create(
    model="Qwen/Qwen2.5-7B-Instruct",
    source="huggingface",
    name="my-deploy",
    gpu={"gpu_type": "A100-80GB", "gpu_count": 1},
    provider="gcp",
)

Serving runs on on-demand VMs (not the Spot capacity used for GCP training).

Where to go next

All serving providers

Compare shapes, status, and the live CLI catalog.

GPU sizing

Match GPU memory to model size.