Darkbloom – Private inference on idle Macs • Hacker News Board

Re: Darkbloom – Private inference on idle Macs

#21

Post by ramoz » Thu, Apr 16, 2026, 5:03 AM UTC

nl wrote: post #6

They use the TEE to check that the model and code is untampered with. That's a good, valid approach and should work (I've done similar things on AWS with their TEE) The key question here is how they avoid the outside computer being able to view the memory of the internal process: > An in-process inference design that embeds the in- ference engine directly in a hardened process, elimi- nating all inter-process communi…

Macs do not have an accessible hardware TEE.

Macs have secure enclaves.

Re: Darkbloom – Private inference on idle Macs

#22

Post by BingBingBap » Thu, Apr 16, 2026, 5:03 AM UTC

Generate images requested by randoms on the internet on your hardware.

What could possibly go wrong?

Re: Darkbloom – Private inference on idle Macs

#23

Post by MrDrMcCoy » Thu, Apr 16, 2026, 5:04 AM UTC

pants2 wrote: post #17

Cool idea. Just some back-of-the-envelope math here (not trusting what's on their site): My M5 Pro can generate 130 tok/s (4 streams) on Gemma 4 26B. Darkbloom's pricing is $0.20 per Mtok output. That's about $2.24/day or $67/mo revenue if it's fully utilized 24/7. Now assuming 50W sustained load, that's about 36 kWh/mo, at ~$.25/kWh approx. $9/mo in costs. Could be good for lunch money every once in a while! Around…

Don't forget to factor in cooling costs.

Re: Darkbloom – Private inference on idle Macs

#24

Post by kennywinker » Thu, Apr 16, 2026, 5:05 AM UTC

foota wrote: post #13

kennywinker wrote: post #8

I have a hard time believing their numbers. If you can pay off a mac mini in 2-4 months, and make $1-2k profit every month after that, why wouldn’t their business model just be buying mac minis?

Capital and availability?

I guess if it only works at scale capital is maybe the answer. Like enough cash to buy 5 or 10 or even 100 minis seem doable - but if the idea only works well when you have 10,000 running - that makes some sense.

Re: Darkbloom – Private inference on idle Macs

#25

Post by pants2 » Thu, Apr 16, 2026, 5:05 AM UTC

You might not even know it as a user but the payment/distribution here is all built on crypto+stablecoins. This is a great use case for it.

Re: Darkbloom – Private inference on idle Macs

#26

Post by todotask2 » Thu, Apr 16, 2026, 5:05 AM UTC

pants2 wrote: post #17

Cool idea. Just some back-of-the-envelope math here (not trusting what's on their site): My M5 Pro can generate 130 tok/s (4 streams) on Gemma 4 26B. Darkbloom's pricing is $0.20 per Mtok output. That's about $2.24/day or $67/mo revenue if it's fully utilized 24/7. Now assuming 50W sustained load, that's about 36 kWh/mo, at ~$.25/kWh approx. $9/mo in costs. Could be good for lunch money every once in a while! Around…

OpenAI has only about 5% paying customers, how does it generate revenue?

I don’t think this is a sustainable business model. For example, Cubbit tried to build decentralised storage, but I backed out because better alternatives now exist, and hardware continues to improve and become cheaper over time.

Your electricity and ownership are going to get lower return and does not actually requce CO2.

Re: Darkbloom – Private inference on idle Macs

#27

Post by pants2 » Thu, Apr 16, 2026, 5:05 AM UTC

MrDrMcCoy wrote: post #23

pants2 wrote: post #17

Cool idea. Just some back-of-the-envelope math here (not trusting what's on their site): My M5 Pro can generate 130 tok/s (4 streams) on Gemma 4 26B. Darkbloom's pricing is $0.20 per Mtok output. That's about $2.24/day or $67/mo revenue if it's fully utilized 24/7. Now assuming 50W sustained load, that's about 36 kWh/mo, at ~$.25/kWh approx. $9/mo in costs. Could be good for lunch money every once in a while! Around…

Don't forget to factor in cooling costs.

Or saved heating costs in the winter!

Re: Darkbloom – Private inference on idle Macs

#28

Post by chaoz_ » Thu, Apr 16, 2026, 5:05 AM UTC

pants2 wrote: post #17

Cool idea. Just some back-of-the-envelope math here (not trusting what's on their site): My M5 Pro can generate 130 tok/s (4 streams) on Gemma 4 26B. Darkbloom's pricing is $0.20 per Mtok output. That's about $2.24/day or $67/mo revenue if it's fully utilized 24/7. Now assuming 50W sustained load, that's about 36 kWh/mo, at ~$.25/kWh approx. $9/mo in costs. Could be good for lunch money every once in a while! Around…

Genuinely curious, is there any way to estimate amortization of Mac?

I’d imagine 1 year of heavy usage would somehow affect its quality.

Re: Darkbloom – Private inference on idle Macs

#29

Post by ramoz » Thu, Apr 16, 2026, 5:06 AM UTC

Unfortunately, verifiable privacy is not physically possible on MacBooks of today. Don't let a nice presentation fool you.

Apple Silicon has a Secure Enclave, but not a public SGX/TDX/SEV-style enclave for arbitrary code, so these claims are about OS hardening, not verifiable confidential execution.

It would be nice if it were possible. There's a lot of cool innovations possible beyond privacy.

Re: Darkbloom – Private inference on idle Macs

#30

Post by xendo » Thu, Apr 16, 2026, 5:06 AM UTC

pants2 wrote: post #17

Cool idea. Just some back-of-the-envelope math here (not trusting what's on their site): My M5 Pro can generate 130 tok/s (4 streams) on Gemma 4 26B. Darkbloom's pricing is $0.20 per Mtok output. That's about $2.24/day or $67/mo revenue if it's fully utilized 24/7. Now assuming 50W sustained load, that's about 36 kWh/mo, at ~$.25/kWh approx. $9/mo in costs. Could be good for lunch money every once in a while! Around…

Any idea what makes for such a diff between your and theirs numbers? Batching? Or could they do a crazy prefix caching across all nodes to reduce the actual processing.