Skip to main content

What is c0mpute?

c0mpute is a decentralized AI inference network. Instead of routing your prompts through corporate data centers, c0mpute connects you directly to a distributed network of GPU workers — regular people sharing their compute power.

AI powered by people, not data centers.

How it works

You send a message. The orchestrator finds an available worker. The worker runs the model on their GPU and streams tokens back to you in real-time. No middleman logging your prompts. No corporate filter deciding what you're allowed to ask.

Two tiers

TierModelCostWhere it runsNotes
ProQwen3 8B Uncensored10 creditsBrowser (WebGPU)~4.3GB / 6GB VRAM, uncensored
MaxQwen3.5 27B abliterated15 credits (20 with deep thinking)Native workersuncensored + web search + vision

Credits and the $ZERO token

Inference is paid for with credits. 1 credit = $0.01, bought with USDC. You don't need any token to use c0mpute.

  • Top up credits with USDC; they're spent per message based on your selected tier
  • Workers earn 70% of the USD value of the credits spent on jobs they complete (80% if they stake), paid in USDC

$ZERO is a separate, value-accrual token. Network revenue automatically buys it back and burns it, and pays a share to everyone who stakes it.

See The $ZERO Token for the full breakdown.

The stack

  • Browser workers use WebGPU via WebLLM to run models directly in the browser tab
  • Native workers use ollama with CUDA, Metal, or Vulkan acceleration
  • The orchestrator is a Socket.io server that handles job routing, worker matching, and real-time token streaming

Why?

Centralized AI providers censor their models, log your prompts, and can revoke access at any time. c0mpute is the alternative — private, uncensored, and owned by no one.

Anyone can use c0mpute or contribute compute and start earning.