Compute marketplace · Early access

Apple Silicon compute. Dedicated AI inference.

Rent an approved Apple Silicon Mac for 30 days of managed text inference. One customer per machine, with no per-token charge. Or create a farmer account and supply an eligible Mac.

Already registered? Renter dashboard/Farmer dashboard

Serving architecture illustration. Availability is shown in the marketplace.

30 days

Published dedicated rental term

1 customer

Per dedicated machine rental

MLX

Model serving on Apple Silicon

Terms and runtime: provider documentation. Paid rentals accrue the provider share approved for that node. Free test allocations earn nothing.

Check supply before you plan a rental.

The September 11, 2026 snapshot recorded no listed machines and zero online nodes. Tier defaults are not machine quotes. Check the current stock response below before funding a rental.

Sources: stock, fleet, tiers.

View current listings

The decision in detail Reviewed 11 Sep 2026

Three model configurations. One dedicated Mac per rental.

The reviewed catalog supports Qwen3.8 27B at 4-bit, 8-bit and BF16 (16-bit). Choose by model requirements and available machines, then evaluate your workload.

Per paid rental term
30 days
Per allocated machine
1 customer
Chat completions and streaming
Text

Qwen3.8 27B · required memory

4-bit24 GB RAM
8-bit48 GB RAM
BF16 (16-bit)96 GB RAM

Zero-based scale. Each metric uses its own unit and scale.

View all catalog values as a table
Qwen3.8 27B configurations · September 11, 2026
FormatRAM (GB)Disk (GB, approx.)Context (tokens)
4-bit241616,384
8-bit483032,768
BF16 (16-bit)965532,768
Catalog requirements, reviewed September 11, 2026. These values describe supported configurations; they do not measure speed or establish inventory.

01 / For renters

Run a catalog model
through the API.

Your application sends model requests. The provider runs the serving process on a dedicated Mac. Choose the model and test the workload that matters to you.

Choose a catalog model

Compare the published 4-bit, 8-bit and BF16 (16-bit) configurations. Match memory and context to the work you need done.

Explore the catalog

Know what you rent

The documented rental supplies a model API for 30 days. Shell access and a remote macOS desktop are outside its scope.

Read the rental guide

Test before you depend on it

Measure task quality, first-token latency and simultaneous requests. Decide how your application handles an unavailable node.

Plan your evaluation

02 / For providers

Your Mac supplies compute.
Your farmer account manages it.

Start with an account at farmer.proxies.sx. It is required to connect a provider node and gives you access to compute management, earnings and payout requests.

Start with a Mac you already own

Check the current model requirements before buying hardware. Paid rentals accrue your approved share; listing and free tests earn nothing. Accrual, settlement and completed payouts are separate states.

Calculate revenue and operating costs

Have an account? Open your compute dashboard.

  1. 01

    Create and verify your farmer account

    An account is required to provide compute. Sign up at farmer.proxies.sx and verify your email before opening protected portal sections.

    Create an account
  2. 02

    Complete the agreement and get your key

    Sign the Partner Agreement, then open Compute in the farmer portal and create a compute agent key. Keep that supply key private.

    Farmer Compute page
  3. 03

    Connect an eligible Mac

    Check memory, free disk and native Node and Python prerequisites. The current installer sets up its own MLX runtime and asks for your supply key.

    Installation guide
  4. 04

    Complete verification and supplier approval

    Wait for model readiness, the platform benchmark and supplier approval of the node and agreement. Review the approved price and provider share, then enable List for rent in your farmer Compute page.

    Compute dashboard

03 / The compute library

Guides for renting and providing compute.

Sourced guides with explicit review dates, practical checks and clear limits on what has been tested.

Choose your inference setup

For renters

04 / For agents and developers

Discover the catalog.
Build around the model API.

Read models, published tiers and stock without credentials. Inference requires a renter account and an active rental. Keep orchestration, retrieval and external tools in your application.

Public discovery · read only

GET /v1/peer/compute/catalog

Models → memory requirements → context limits
Match the catalog to current marketplace stock.

Proxy MCP and x402 integrations are documented separately. They do not establish compute purchasing support. Proxy access for agents.

Before you rent or list a Mac

What does dedicated compute provide?
One customer's model requests use the rented Mac for a published 30-day term. Your application calls an inference API. For Xcode builds, remote desktop or arbitrary server software, compare a service with operating-system access. Compare access and workloads.
How much memory does a provider need?
The September 11 catalog requires 24 GB for its 4-bit model, 48 GB for 8-bit and 96 GB for BF16 (16-bit). The current installer requires at least 26 GB free disk for the smallest setup. Benchmark and supplier approval determine admission. Check Mac requirements.
Does the API support every agent feature?
The customer documentation supports chat completions and streaming, with a 4096-token output cap and 60 requests per minute per rental. It rejects tools, stop sequences and response_format fields. Check that contract before choosing the endpoint for your application. Review the API limits and key scopes.
What happens to prompts and responses?
The published policy allows temporary relay storage. Completed-job content is normally scrubbed after one hour; job records expire after 24 hours, subject to cleanup timing. Suppliers administer their own Macs. Read the privacy evidence and limits.

Sources reviewed September 11, 2026: provider requirements, model catalog, customer documentation. Customer documentation was reviewed in its public application bundle; opening the dashboard requires sign-in. These are documented terms, not results from an authenticated rental test.

Choose your starting point

Find inference for your application.
Or bring a Mac to the network.

Published by PROXIES.SX. The product snapshot records September 11, 2026; each guide displays its own source review date. Provider signup and portal routes were reviewed September 11. No authenticated rental, provider installation, payout or hardware benchmark was performed for these guides.