What is Darkbloom
A new topology for private inference.
Darkbloom routes inference requests to verified Apple Silicon hardware. Requests are encrypted hop by hop, and providers process prompts to run inference. Mac owners contribute compute they already own.
Run a provider on hardware you already have. Darkbloom matches your Mac to demand it can actually handle.
Why does it cost less
Darkbloom turns idle capacity into a private inference market
Typical inference passes through clouds, resellers, and API layers, each adding margin. Darkbloom routes requests to idle Apple Silicon instead - hardware its owners already paid for, where the marginal cost is mostly electricity. Pay per token; see the current pricing page for rates.
Decentralized Inference Pricing
Pay for inference by token usage. Input, output and cache-read tokens have separate model-specific rates, quoted in USD per million tokens.
Why privacy matters*
Sensitive information shouldn't run on untrusted hardware
Requests are encrypted hop by hop. The coordinator decrypts requests in confidential-VM memory for routing and billing, does not log or retain prompt content, and re-encrypts each request to the provider’s attested key. The provider is the plaintext endpoint; this is not end-to-end encryption between consumer and provider.
- Encrypted
- Verified hardware
- Private
How privacy is ensured*
Verified hardware, explicit trust boundaries
Darkbloom combines encrypted transport with hardware and code verification. These checks help establish which provider receives a request. The coordinator decrypts in confidential-VM memory, and the provider processes plaintext to perform inference.
Trust includes the coordinator and the provider plaintext endpoint
What powers the grid
Decentralized inference on Apple Silicon mac hardware
The grid runs on fleet of consumer Macs, M1 through M5. High-memory machines powering a range of open-source models and the router assigns each request to the most capable available machine automatically.
How much can providers earn
Earn from compute
you already own
Darkbloom pays you a base reward just for staying online, plus usage earnings on top every time your Mac serves a real inference request. Earnings scale based on your chip and memory - the more capable your machine, the more it can run.
Estimated monthly earning
$204.89/mo
$2,458.64/yr at 60% duty cycle
- Mac model
- MacBook Pro
- Chip family
- M4 Max (16-core)
- Unified memory
- 128 GB
This estimate assumes a 60% duty cycle - the share of time your Mac is actively producing output tokens. Actual earnings may vary.
Models your Mac can run
Models are ranked by estimated monthly earning at the selected duty cycle.