Provider guide

Run models from your Mac.

Umbra providers host public Hugging Face models on Apple Silicon. The console is for operations; this page is the plain setup guide for humans and AI agents.

Create account Open provider console Read attestation spec

Hardware

Apple Silicon Mac

Memory

36 GB recommended

Model source

Public HF repos

Prompt access

Not logged or persisted

Setup Steps

Install the provider binary. Use the signed Umbra CLI on macOS 15 or newer.
```
curl -fsSL https://umbra.dev/install | sh
```
Pair this Mac. Run login, then enter the device code in your Umbra account.
```
umbra login
```
Add your Hugging Face token locally. Use a read-only token. It is stored on the Mac and used only for public model downloads.
```
umbra hf connect
```
Approve a public model. In the provider console, approve a Hugging Face repo and pin its digest before serving it.
Start serving. Routing begins after attestation, memory, and warm-model checks pass.
```
umbra serve
```

What Umbra Checks

Before traffic routes

Secure Enclave device key is present.
SIP and Apple attestation checks pass.
The model is warm and its digest matches the approved repo.
Enough memory remains for model weights and KV cache.

What stays local

Your Hugging Face token.
The provider device private key.
Downloaded model weights.
Buyer prompts and outputs after request completion.

AI Agent Notes

Task target: set up a provider Mac. Do not ask for secrets in chat. Ask the operator to paste the Hugging Face token into the local CLI. Never upload the token to Umbra. After setup, use `/console/provider`, `/console/provider-models`, `/console/provider-trust`, and `/console/provider-payouts` for operations.

{
  "provider_setup_url": "/providers",
  "console_urls": [
    "/console/provider",
    "/console/provider-models",
    "/console/provider-trust",
    "/console/provider-payouts"
  ],
  "required_local_commands": ["umbra login", "umbra hf connect", "umbra serve"],
  "secret_handling": "HF token stays on the provider Mac"
}