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.

Three tiers

TierModelCostWhere it runsNotes
FreeQwen 1.5B0 creditsBrowser (WebGPU)~900MB, fast, basic
ProDolphin Mistral 7B10 creditsBrowser (WebGPU)~4GB VRAM, uncensored
MaxQwen2.5 14B abliterated50 creditsNative workers~9GB, uncensored + web search

The $ZERO token

$ZERO is the credit token that powers c0mpute. 1 $ZERO = 1 credit.

  • Deposit $ZERO to your c0mpute account to get credits
  • Credits are spent per message based on your selected tier
  • Transaction fees from $ZERO trading fund the worker reward pool
  • Workers earn SOL for every job they complete

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 node-llama-cpp 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.