Skip to main content

Documentation Index

Fetch the complete documentation index at: https://www.thundercompute.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

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 Cheap 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
# Launch an Ollama instance
tnr create --template ollama

# Launch ComfyUI
tnr create --template comfy-ui

# Launch Forge Neo
tnr create --template forge-neo

# Launch Unsloth
tnr create --template unsloth
  1. Check the instance is ready
tnr status
Wait until the status shows the instance is running before connecting.
  1. Connect to the instance
tnr connect 0   # replace 0 with your instance ID
Port forwarding is handled automatically when you connect. The -t flag is unnecessary.
  1. Start the service
# Ollama
start-ollama

# ComfyUI
start-comfyui

# Forge Neo
start-forgeneo

# Unsloth
start-unsloth
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.