Share Compute

Your Mac serves the models. You earn API credit.

Share Compute connects an idle Apple Silicon Mac to the QuickSilver Pro pool. It answers real customer requests for the open-weight Qwen 3.8 27B with Rapid-MLX, and every token it serves earns credit you can spend on any model we host.

Get a provider keyHow to start

80% of what customers pay, as API credit. No port forwarding. Stop anytime.

How it works

Customer app
QuickSilver API
Pool relay
Your Mac

Your Mac dials out to the relay over one encrypted WebSocket. Nothing ever connects in to your network.

One outbound connection

No inbound ports, no port forwarding, no public IP. Your Mac opens a WebSocket to the relay, and requests arrive on it in real time. There is no job queue to poll.

Real requests, served locally

Rapid-MLX runs the model on your Mac's GPU and streams answers back. The pool routes each conversation to the same machine, so your Mac's prompt cache keeps follow-up turns fast.

Credit for every token

QuickSilver counts the tokens itself and credits your account balance. If your Mac is busy or offline, the request goes to a cloud provider instead, and the customer never notices.

The model you can serve today

Qwen 3.8 27B is the pool's launch model. The rates below show what you earn at today's list prices (80% of the QuickSilver price, per 1M tokens); each request actually pays 80% of what that customer was charged.

You earn (input / output per 1M)

Qwen3.8 27B
$0.272 / $1.632
qwen3.8-27b
Recommended Mac

M3/M4 Max or Ultra with 36 GB+ unified memory. Dense 27B models need Max-class GPU throughput to answer quickly.

Your rate follows our price list automatically. More models will be added later.

Start sharing in four steps

  1. 1

    Create a provider key

    Sign in and open Share Compute in your dashboard. Create a provider key (it starts with qsppk-). It can only register machines for your account. It cannot spend your balance. Open the dashboard

  2. 2

    Install Rapid-MLX

    Rapid-MLX is the open-source MLX inference engine for Apple Silicon. You need version 0.15.3 or later; if Homebrew still offers an older release, use the uv line instead.

    bash
    brew install rapid-mlx
# or, if Homebrew is still on an older release:
uv tool install rapid-mlx@latest
  3. 3

    Start sharing a model

    Run this in Terminal and paste your provider key when prompted, so the key stays out of your shell history. The model downloads once if needed. Use a different --worker name on each Mac, and press Ctrl-C to stop.

    bash
    rapid-mlx share qwen3.8-27b --quicksilver --worker "$(hostname -s)"

    Prefer an app? In Rapid-MLX Desktop, turn on Share Compute under Settings → Experimental, pick a model in Live Pool, and click Connect & serve. Download Rapid-MLX Desktop

  4. 4

    Watch your credit arrive

    Earnings are settled hourly. To see them in Rapid-MLX, create a read-only key (qsprk-) in the dashboard and add it under Credits. That key can only read your earnings.

Not on a Mac?

The pool protocol works with any machine that runs an OpenAI-compatible server (vLLM, llama.cpp, Ollama, LM Studio). Use the open-source reference client to connect it. quicksilver-pool-node on GitHub

Read the full Rapid-MLX Share Compute guide

What you earn, exactly

You earn 80% of what customers pay for every request your Mac serves. Your rate follows QuickSilver's price list automatically: when a model's price changes, your earnings change with it. QuickSilver keeps 20%, and a payout can never exceed what the customer paid. Earnings are paid hourly as QuickSilver API credit, not cash, up to $20 per node per month.

80% of what customers pay

For every request your Mac serves, you earn 80% of what the customer actually paid for it. QuickSilver keeps 20%, and a payout can never exceed the customer's charge.

Follows our price list

Your rate is not locked in. It tracks QuickSilver's price list automatically, so when a model's price goes up or down, your earnings change with it.

Settled hourly

Work is credited to your balance every hour. A delayed settlement is paid later and never paid twice.

API credit, not cash

Earnings go to your QuickSilver account balance and pay for API calls on any of our models. There is no cash-out, bank transfer, or crypto payout, and credit cannot be transferred.

Monthly cap per node

To limit fraud, each node can earn up to $20 per calendar month (UTC). Anything above the cap is not paid and does not carry over.

Your own traffic doesn't count

API calls paid for by your own account earn nothing, even when your Mac serves them. You can't pay yourself.

Your responsibilities as a contributor

Your Mac processes real customer prompts and completions. Customers trust us with that data, so by sharing compute you agree to handle it with care.

  • Don't log, keep, or read customer content. Run the node with request logging off, and never store, inspect, or reuse prompts or completions.
  • Don't tamper with outputs. Serve the listed model unmodified, and never alter, filter, or fabricate responses.
  • Usage is measured by us. QuickSilver counts tokens itself and ignores what the node reports. Nodes whose reports don't match are flagged for review.
  • We can remove nodes. We may remove a node, and withhold credit earned through abuse, if it breaks these rules or degrades service. To take your machine out of the pool for good, email [email protected].

Contributor terms are part of our Terms of Service · Privacy Policy

Frequently asked questions

Put your Mac to work

Create a provider key, run one command, and your Mac starts earning API credit on real traffic.

Get a provider key