Malibu

Open-model inference on real Macs. Private, verifiable, cheaper.

Mac owners host open models on idle Apple Silicon and earn USDC today. Developers point Cursor, Cline, or Aider at one API endpoint. $MALIBU is the planned network token — at launch, every prompt pays providers, burns supply, and grows the floor.

Signedevery response · verifiable
tokens served
requests
nodes online
GB/s bandwidth
GPU cores
CPU cores
GB unified RAM
models serving

Two ways in

Build with the API or host a Mac. Real hardware, real models, real settlement.

Malibu console for running AI models
Build
OpenAI-compatible API for agents & coding tools.
Malibu host app earning from a Mac
Host
Earn USDC from idle Mac time.
$MALIBU at token launch.
New

Agent-readable onboarding.

Point your coding agent at https://get.malibu.tech/skill.md. It can install the provider CLI, check status, recover a broken setup, update or uninstall, and connect apps to the OpenAI-compatible API at api.malibu.tech.

https://get.malibu.tech/skill.md
For developers

The OpenAI SDK is the Malibu SDK.

Point any OpenAI-compatible client at api.malibu.tech/v1. Streaming, tool calling, structured output, sticky conversations, and signed inference receipts — all live today.

from openai import OpenAI
client = OpenAI(
  base_url="https://api.malibu.tech/v1",
  api_key="mp_…"
)
Cursor Cline Codex Continue Aider Roo Code LangChain

Cheaper by design

Distributed Apple Silicon undercuts hyperscaler GPU pricing on open models. Pay per token, not per H100-hour.

Cooperative trust

Prompts route to individual Macs as plaintext — not confidential compute. Signed receipts bind the response. See the security docs.

Signed receipts

Every response carries an Ed25519 receipt you can verify offline with malibu-verify.

Open model catalog

Llama, Qwen, GPT-OSS, and more — one endpoint, no per-provider onboarding.

Drop-in OpenAI SDK

Change base_url, keep your code. Streaming, tool calling, structured output all work.

Prepaid credits

Top up once, no subscription. GitHub OAuth for the API key; no wallet required to start.

For Mac owners

Your Mac already has the hardware.

Download Malibu for macOS, click Launch Provider, and your Apple Silicon Mac joins the pool. Malibu picks the right open model for your memory tier, serves when you're idle, and pays you in USDC (90% of billed credits). Or point a coding agent at get.malibu.tech/skill.md. $MALIBU emission is planned at mining launch.

Paid in USDC today

Every billed prompt credits USDC. Payouts settle to your wallet weekly. $MALIBU minting is not live yet.

Runs on pennies

Apple Silicon draws 20–40W under inference load. Passive income, not a power bill.

Your Mac stays yours

Cooperative scheduling — serving interrupts for milliseconds. No datacenter, no rack.

Zero configuration

Malibu picks the right open model for your memory tier at install time. No tuning. Invite required to register.

Early providers at launch

When mining ships, the first 90 days are designed to mint 5× more $MALIBU per prompt. Not paying today.

Pause anytime

Toggle serving on when idle, off when you're working. No commitment, no schedule.

Models & pricing

Frontier open models, MLX-native.

A curated catalog of the strongest open-weight models — quantized for Apple Silicon, matched to provider hardware at install time. Qwen2.5 7B, Qwen3.5 35B, Llama 3.3 70B, and gpt-oss 120B are in the catalog and serve when a matching-RAM Mac is online. Pricing tracks the OpenRouter frontier — compare the live rate card, no subscription, no seat license.

Qwen3-Coder
Agentic coding · Frontier
Qwen2.5 Coder 7B
Fast local coding · 7B
Llama 3.3 70B
Frontier reasoning · 70B
Qwen3.5 35B
Balanced general · 35B
gpt-oss 120B
Flagship OSS · 120B
Llama 3.2 3B
Low latency · 3B

A single Mac Studio Ultra already runs frontier open models — gpt-oss 120B — from unified memory, no datacenter. Pooling Macs to serve models beyond any single machine is next on the roadmap; a verifiable receipt is worth the most exactly at that scale. Not live yet.

For holders

The network is the token

Today, billed inference pays providers 90% in USDC. At token launch, every dollar of buyer spend is designed to split: providers get paid, supply burns, reserves grow.

Hold $MALIBU, own the network — that's the launch design. Live billing is 90/10 USDC, not the burn-and-reserve split.

Read the litepaper →
At token launch — every $1

Three things happen the moment a prompt clears under token economics. Not the live 90/10 USDC rail.

Pay

The Mac gets paid.

70¢ of every dollar goes to the person whose Mac ran the prompt, in USDC.

70¢ of every $1
Burn

Supply shrinks.

18¢ buys $MALIBU on the open market and burns it. Every prompt leaves fewer tokens in circulation.

18¢ burned
Back

The floor rises.

12¢ goes into a reserve that backs every new $MALIBU. Macs keeping the network up earn the new tokens.

12¢ to reserve
70¢ + 18¢ + 12¢ = $1 Burn beats reserve every day the network is used