Create an Instance
- Log in to the console
- Click Create Instance
- A dialog will open—select your mode, GPU, CPU, disk size, and template
- Click Launch
Configuration Options
The console provides the same configuration options as the CLI and extension:- Mode: Prototyping or Production
- GPU Type: A6000, A100, H100 (availability depends on mode)
- GPU Count: 1 GPU for most prototyping GPUs; H100 prototyping supports 1-2 GPUs. Production supports 1-8.
- vCPUs: Options vary by GPU type and count (prototyping only)
- Disk Size: 100GB to 400GB (prototyping) or 1000GB (production)
- Template: Base, Ollama, ComfyUI, and more
Mode Selection
Choose between optimized development pricing or full compatibility:- Prototyping (default): Lower cost with CUDA-level optimizations. Best for development.
- Production: Standard VM with full compatibility. Best for long-running jobs and production workloads.
GPU Options
| GPU | VRAM | Availability |
|---|---|---|
| A6000 | 48GB | Prototyping only |
| A100 | 80GB | Both modes |
| H100 | 80GB | Both modes |
Templates
Templates pre-configure your instance for common AI workflows:| Template | Description |
|---|---|
base | Ubuntu with PyTorch + CUDA |
ollama | Ollama server environment |
comfy-ui | ComfyUI for AI image generation |