Deploying Instances
This guide walks you through deploying a GPU instance on Runcrate.
Prerequisites
Before deploying, make sure you have:
Step-by-Step Deployment
1. Open the Deploy Page
Navigate to Dashboard > Instances > Deploy Instance, or go directly to runcrate.ai/dashboard/instances/deploy.
2. Choose GPU Type and Count
Select the GPU model that fits your workload. You can deploy multiple GPUs on a single instance for multi-GPU training.
| GPU | VRAM | Recommended For |
|---|
| RTX 4090 | 24 GB | Inference, fine-tuning |
| L40S | 48 GB | Large model inference, medium training |
| A100 40 GB | 40 GB | Training, research |
| A100 80 GB | 80 GB | Large-scale training |
| H100 | 80 GB | Maximum performance |
- CPU cores — More cores help with data preprocessing and multi-threaded workloads.
- RAM — Ensure enough memory for your dataset and model. A good rule of thumb is 2x your GPU VRAM.
- Disk — Local NVMe storage for your code, datasets, and model weights.
4. Select a Region
Choose from available regions. Availability of specific GPU types may vary by region.
Select the region closest to you for the lowest latency SSH experience.
5. Choose an OS Image
Select a pre-built image with the tools you need:
| Image | Includes |
|---|
| Ubuntu + CUDA | Ubuntu 22.04, CUDA 12.x, cuDNN, Python 3.10+ |
| PyTorch | Everything in Ubuntu + CUDA, plus PyTorch pre-installed |
| TensorFlow | Everything in Ubuntu + CUDA, plus TensorFlow pre-installed |
6. Attach an SSH Key
Select one or more SSH keys to authorize for the instance. If you have not added a key yet, you can do so from Dashboard > SSH Keys.
7. Optionally Attach Storage
You can attach a persistent storage volume to your instance. This keeps your data safe across instance terminations. See Storage for details.
8. Review and Deploy
Review your configuration and estimated hourly cost, then click Deploy.
Cost Estimation
Your hourly cost is determined by:
Hourly Cost = GPU cost x GPU count + CPU cost + Memory cost + Storage cost
Deployment Time
Instances typically take 1-3 minutes to go from creating to deployed. You will see the status update in real time on the Instances dashboard.
Enable auto-recharge in your Billing settings to ensure your balance never runs out and your instances are not interrupted. What Happens Next
Once your instance status shows Deployed:
- Copy the SSH command from the instance details.
- Connect via terminal or VS Code.
- Start building.
See Connecting to Instances for the full connection guide.
