​

Malibu Litepaper

The world’s biggest AI cloud already exists. Malibu turns it on.

​

The premise

Two hundred million Apple Silicon Macs have shipped since 2020 (methodology). Together they are the largest idle Apple Silicon compute pool we can point at in public docs. Each machine delivers roughly ten times the per-watt efficiency of an RTX 5090 on Proof-of-Model-Walk memory-hard weight walks (Phase 1 benchmark, M5 Air, July 2026 — not inference TPS). Fleet idle-time figures are planning assumptions, not audited telemetry — see Benchmarks & methodology. Malibu turns Apple Silicon Macs into a coordinated inference network. Every admitted provider can earn from billed requests. Token-protocol conversion of buyer dollars into $MALIBU demand is planned — see Economics. Malibu doesn’t build new AI infrastructure. It activates the infrastructure already sitting on millions of desks.

​

The opportunity

AI inference is a fifty-billion-dollar market growing three-to-five times a year. Three companies own most of it. Open-source models — Llama, Qwen, gpt-oss — match closed-model quality on many chat, coding, and retrieval workloads (not every reasoning or multimodal eval). Supply hasn’t. Buyers often pay a large markup over the underlying compute. New datacenter capacity takes billions of dollars and years to permit. Meanwhile hundreds of millions of AI-capable Macs sit on desks running at low utilization (the “four percent” figure is a planning assumption, not measured fleet telemetry). Every prior decentralized AI network — Bittensor, Akash, Gensyn, Prime Intellect — hit the same wall: buyers won’t come without providers; providers won’t stay without buyers. A decade of permanent bootstrap. Malibu’s bet is to pay providers to be ready before buyers arrive (PoMW + emission at v0). Today’s live product is the inference marketplace (credits and receipts) on a small invite-gated pool. USDC-on-Base payout ships at public beta. Check Network status for the ledger.

​

Why now

Five years ago this network wasn’t possible. Today, four preconditions are simultaneously true for the first time:

• Apple Silicon. Unified-memory Macs capable of serving large open-source models are shipping in consumer hardware.
• Open-source frontier models. Llama, Qwen, gpt-oss now match closed-model quality on many workloads. Verified inference on open weights is finally worth paying for.
• Cheap inference verification. TOPLOC (Prime Intellect, 2025) is designed to verify buyer responses at roughly one percent of serving cost — planned v1 on Malibu, not live. Receipts are live today.
• Stablecoin payments. USDC on Base makes global micropayments settlement-final in seconds, at sub-cent cost.

Malibu is not early to any of these. It is the network that combines all four.

​

What we’ve shipped

Malibu is a live coordinated inference network today — distributed Apple Silicon providers, centralized routing and billing. Real coordinator, real providers, real inference requests, real credit ledger. Admission is private pre-beta: a valid invite is required to register a new provider. USDC-on-Base payout ships at public beta.

​

Inference marketplace — Live

• Coordinator service. Live Provider admission, real-time request routing, per-request billing ledger, epoch settlement.
• Gateway. Live OpenAI-compatible /v1/chat/completions, /v1/models, /v1/usage, /v1/rate-card, /v1/stats/overview at api.malibu.tech. GitHub OAuth for buyer signup. Quota reservation. Signed session receipts.
• Provider onboarding. Beta Signed installer; RAM-tier model match; launchd watchdog. Invite required for a fresh register (malibu.tech/host). Already-running providers update without a new invite.
• Agent-readable onboarding. Live Point a coding agent at get.malibu.tech/skill.md to install, inspect, recover, update, or uninstall the provider CLI, and to connect apps to api.malibu.tech. Same invite gate.
• End-to-end serving. Live Buyer → gateway → coordinator → Apple Silicon provider → response → signed receipt → settlement. Public snapshot: api.malibu.tech/v1/stats/overview.
• Multi-turn tool calling. Live Standardized tool_calls[] emission and second-turn role: "tool" acceptance on catalog-marked templates. Buyer frameworks must validate before execution — Buyer-side validation.
• Structured output. Live response_format: json_schema with the OpenAI strict-mode subset.
• Sticky conversations. Live Stable conversation_id; cached_prompt_tokens in the OpenAI usage object.
• Signed inference receipts. Live v0.3 nine-field receipt, Ed25519. Verify with malibu-verify.
• Verified model settlement. Live Missing or unverifiable receipts settle with zero provider credits. Late receipts are non-settling.
• Rate card & billing. Live Credit-based metering, 90% default provider share today. USDC-on-Base payout is planned for public beta. See Economics.
• Model catalog. Live Qwen2.5 (7B), Qwen3.x (8B–35B-class), Llama-3.2 (3B), Llama-3.3 (70B), Gemma, gpt-oss (20B / 120B) — MLX-native, RAM-tier matched. Routes when a matching-RAM Mac is warm. Snapshot of who’s online: api.malibu.tech/v1/stats/overview. Details: Model catalog.
• Routing tiers. Live New Macs join provisional; operator promotion to pinned raises routing weight. See Payments.
• Release cadence. Live Signed installer on GitHub Releases; public download follows GitHub Latest via malibu.tech/host.

​

Token protocol — Planned

• PoMW mining substrate. Prototype Metal port is public and reproducible. Two hundred verification vectors passed byte-exact against a Rust reference on Qwen3-1.7B GGUF weights. Phase 1: 2.14 million walks per second at 4.7 watts on an M5 Air (walk workload, not inference).
• v0 mining launch: Planned v0 on-chain emission, burn-and-mint fee split, token-native settlement.
• v1 marketplace: Planned v1 TOPLOC per-request verification (Prime Intellect lineage) on buyer-paid inference.
• Pooled serving: Planned multi-Mac models beyond one machine’s unified memory.

This is a launch document for a network that already runs inference — and a protocol layer still activating.

​

What Malibu lets you do

Imagine opening your Mac in the morning and realizing it earned money while you slept. No fans screaming. No datacenter. No rack space. No electricity bill worth noticing. Just your laptop, quietly serving AI requests to buyers who need them, all day. Your Mac is no longer just a laptop. It’s an income-producing asset — not a hobby, not a lottery ticket, an actual asset. A single high-RAM Mac can serve large open models from unified memory. The models that dominate industry inference spend are larger still; pooled serving (several Macs over a local interconnect) is the growth vector for those — on the roadmap, not live. And the bigger the model, the more a verifiable receipt is worth — when you pay frontier rates, an attestation is the only way to know the endpoint ran the weights you paid for, not a cheaper stand-in. Under early-network base-case assumptions (Year 1, ~100–360 providers) (illustrative, not guaranteed, token-regime — see Provider economics): The payback references below are explanatory sensitivity checks against estimated hardware cost, not live payout guidance, not an investment-return proposal, not a forecast, and not a recommendation to buy hardware or tokens. They assume you already own the Mac or independently planned to buy it, and they stress-test the tokenomics model rather than promising any outcome.

• Mac Studio Ultra: roughly $10,000 to$13,000 per year at $MALIBU =$0.005. Around **$40,000+** at$0.02. Hardware payback in under twelve months at the base case. Even under the lower $0.002 scenario, payback is under twenty-four months.
• M4 Max: roughly **$5,100 per year** at$0.005. Around **$20,000** at$0.02. Payback in under a year at the base case.
• M4 Pro: roughly **$3,400 per year** at$0.005.
• Air: roughly **$1,050 per year** at$0.005.

Those figures are not live USDC marketplace payouts. Today you earn 90% of billed credits. Fanless Macs throttle under sustained load — apply a duty-cycle discount (Provider economics). Cooperative scheduling keeps the Mac yours. Mining (planned) runs in the background; serving interrupts for milliseconds at a time. For the first time, the compute you already own can pay you back.

​

What buyers get

On comparable OSS SKUs, Malibu is often cheaper than aggregator list — sometimes a lot cheaper on small models, sometimes even or slightly higher on 20B–32B rows. Dated snapshot: Pricing comparison. Live card: api.malibu.tech/v1/rate-card. Every response carries a signed receipt you can verify offline. The catalog is the OSS frontier: Qwen2.5 7B, Qwen3 families (including 35B-class), Llama 3.2 3B, Llama 3.3 70B, Gemma 4, gpt-oss-20b and gpt-oss-120b — they run when a matching-RAM Mac is in the pool (Model catalog). Billed over drop-in OpenAI-compatible endpoints; credits accrue now, USDC payout at public beta. Why buyers switch:

• Cheaper on many OSS rows. Verify against the snapshot; do not assume a flat 20–40% on every SKU.
• Receipt-verified. Signed binding of (prompt, output, model, provider). Per-request forward-pass attestation via TOPLOC ships at v1 — not live on buyer traffic today.
• OSS-native. Best model per task, when that model is warm. No vendor deprecating a closed SKU next quarter.
• Cooperative trust. Not confidential compute — prompts route through providers as plaintext. See Security & trust model and Threat model.
• Buyer-side validation. Emitted tool_calls[] are model output, not provider-verified intent. See Buyer-side validation.
• No lock-in. Change providers without changing OpenAI-SDK code.

Malibu is designed to be adopted without changing anything on the buyer side except the endpoint.

​

How it works

Every provider runs one binary. At mining launch it performs Proof-of-Model-Walk — a byte-exact 256-step walk through the canonical open-source model’s weights, terminated by a cryptographic commitment. Deterministic. Verifiable in microseconds. The walk hashes over the same weight file the network sells inference for, using the same Metal integer pipeline. Every mined block is a receipt that a specific Mac exercised the memory substrate inference depends on. When a buyer request arrives at v1, the miner yields in ~50 milliseconds — weights already resident, pipeline already running, file already the file the buyer is paying for. Mining state is serving state. That equivalence is the architectural bet the whole network is built on. It is not enforced in production today. Verification is cheap. PoMW verifies in microseconds. TOPLOC (Prime Intellect, 2025) will verify buyer responses at about one percent of serving cost at v1.

​

The token flywheel

Every dollar entering Malibu is designed to strengthen the network. Providers get paid. Reserves grow. Tokens are bought and burned automatically. When a buyer pays $1 for inference under token economics:

• 70¢ goes to the provider who served the request.
• 12¢ grows a protocol-owned reserves floor — held in USDC, on-chain, backing the token’s minimum value.
• 18¢ automatically buys $MALIBU on the open market and destroys it.

No oracle. No governance vote. No token-holder decision. Every transaction is protocol-enforced $MALIBU demand and protocol-owned reserve growth. The token, minted through work, is burned through use. Provider issuance runs on a deterministic emission curve — front-loaded to bootstrap the fleet, tapering as buyer USDC replaces it.

​

Why Malibu wins

1. Apple already shipped the hardware. Two hundred million Apple Silicon Macs. Strong per-watt PoMW efficiency on consumer silicon. Deployed, paid for, and idle.
2. PoMW is designed to prepare the fleet before buyers arrive. Providers earn from day one of mining launch for verifiable useful work. That layer is not paying in production yet.
3. Receipts today; TOPLOC at v1. Signed receipts bind every response now. TOPLOC adds per-request forward-pass attestation when that milestone ships.
4. Every transaction is designed to strengthen the token. At launch, buyer USDC automatically buys and burns $MALIBU; reserves grow. Not active on today’s 90/10 credit rail.
5. The network compounds. Every new provider increases coverage. Better coverage attracts more buyers. Buyer revenue increases provider earnings. Higher earnings attract more providers.
6. The combination is the bet — not a monopoly on the pieces. Akash, Prime Intellect, Render, and io.net already cover overlapping slices (decentralized compute, verification lineage, GPU marketplaces). Malibu’s edge is Apple Silicon + receipts now + PoMW-before-demand as a token mechanism those businesses have little reason to copy. The hardware is not Malibu’s. The mechanism has to come from outside Apple, OpenAI, and the hyperscalers.

​

Join

The world’s biggest AI cloud already exists. Malibu turns it on. The live pool is a small pre-beta (single-digit Macs on the 16 Aug 2026 snapshot — Network status). Emission economics, when they ship, are designed to pay early miners more; mining reputation is designed to transfer to serving priority at v1. Apple built the hardware. Malibu gives it a job.