Skip to main content
Thunder Compute gives indie developers, researchers and data scientists instant access to affordable cloud GPUs. Our pre-configured instance templates set up popular AI stacks automatically, so you can run LLMs or generate AI images in minutes.

​
AI Templates on Low-Cost Cloud GPUs

We currently offer:
  • Ollama – launches an Ollama server for open-source large language models
  • ComfyUI – installs ComfyUI for fast AI-image generation workflows
  • Forge Neo - installs Forge Neo with a basic Stable Diffusion model
  • Unsloth - installs Unsloth Studio for LLM inference and fine-tuning

​
Deploy a Template

  1. Create an instance
  1. Check the instance is ready
Wait until the status shows the instance is running before connecting.
  1. Connect to the instance
Port forwarding is handled automatically when you connect. The -t flag is unnecessary.
  1. Start the service
Required ports forward to your local machine automatically.

​
Template Details

​
Ollama Template

  • Forwards port 11434
  • Access the API at http://localhost:11434
  • Ready for popular Ollama models

​
ComfyUI Template

  • Forwards port 8188
  • Mounts the ComfyUI directory to your Mac or Linux host
  • UI at http://localhost:8188
  • Includes common nodes and extensions

​
Forge Neo Template

  • Forwards port 7860
  • UI at http://localhost:7860
  • Ready for Stable Diffusion

​
Unsloth Template

  • Forwards port 8000
  • UI at http://localhost:8000

​
Need Help?

Encounter problems or have questions? Reach out to our support team any time.