Setup guide download, sign in, host. about 5 minutes.
Umbra turns an idle Apple Silicon Mac into a private inference provider. The CLI does the work on your machine: it signs you in, registers the device, then pulls and serves a model. The platform sets every price, so you just pick what is worth running. Three steps below.
Install the CLI macOS · Apple Silicon
One line in Terminal. It downloads the signed CLI and puts it on your PATH; everything else runs through it. No account needed to install.
curl -fsSL https://tryumbra.dev/install | shRun umbra login
The first run signs you in, or signs you up on the spot if you are new (you can also create an account first). Your device then auto-registers under your account with its name, chip, and unified memory. No keys to paste, no device to add by hand.
umbra loginHost a model
umbra hostlists the models that fit your Mac, each with the platform price and your projected earnings. Pick one and the CLI pulls it, verifies it (the Hugging Face repo plus the GGUF digest), and starts serving. Run it again any time to add another model.
# see what fits, then host one of the listed models
umbra host
umbra host <model-id>What would your Mac earn?
Earnings depend on your chip, unified memory, and how much demand a model sees. The calculator shows what a Mac like yours could earn before you install a thing, with the platform price and projected payout per model.