Skip to content

Run an Ollama model on your GPU

Choose a model that fits the rental and use its authenticated application endpoint.

Published on Oct 12, 2026 | Product: GPU

Before you start

Use an available Ollama-compatible template. Check model license, download size, GPU memory, and free workspace space.

Steps

  1. Wait for the GPU instance and Ollama service to be ready; inspect container logs.
  2. Connect using the published application endpoint and rental-specific authentication, or use SSH for local model management.
  3. Pull a small model that fits the selected GPU. Keep model storage in the template’s persistent workspace.
  4. Run a short prompt and inspect GPU usage. Larger contexts and concurrent requests need additional memory.
  5. Save your application configuration and model choice. Use the same persistent rental when resuming work.

Check the result

The model returns an answer and GPU usage confirms acceleration for the workload.

Troubleshooting

A successful download does not mean a model fits in VRAM. Use a smaller or quantized model, reduce context length, and verify the image’s model storage path. The application token is distinct from the console API key.

Last updated October 12, 2026. Availability and prices are shown in the console before checkout.
Still need help? Open a support ticket with your service name, the time of the issue, and a redacted error message. Never include passwords or API keys.
Categories
Billing and support CLI and developer tools DocVault AI GPU Cloud GPU applications Getting started Hosting and DNS Managed AI APIs Object Storage VPS
Products
DocVault AI GPU Object Storage Shared Hosting VPS