A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices
acossta
243 points
96 comments
October 13, 2026
Related Discussions
Found 5 related stories in 107.8ms across 9,386 title embeddings via pgvector HNSW
- Apple Silicon and macOS VMs: Faster LLM Inference with llama.cpp frabonacci · 289 pts · August 11, 2026 · 60% similar
- Launch HN: machine0 (YC S26) – Persistent CPU and GPU VMs from the CLI bwm · 70 pts · August 18, 2026 · 55% similar
- We Rebuilt the Linux MicroVM Stack on Apple Silicon signa11 · 143 pts · August 21, 2026 · 55% similar
- Building a Linux GPU Driver for the M4 Mac Mini in One Month ADevWithAnIdea · 236 pts · September 15, 2026 · 54% similar
- Apple May Return to Server Market with Nvidia Technology tosh · 18 pts · September 16, 2026 · 53% similar
Discussion Highlights (20 comments)
Bric3d
They'll throw this together but still not sell you something you can stick in a rack ?
simbas
That's why the button is on the underside.
sdoering
Pardon me not understanding what this is about? Basically SETI for AI workloads? At least, this is the impression the landingpage left me with. I am a bit lost, tbh.
veexx103
This project sounds good. What is it actually like?
tom1337
I guess for companies this can be nice? Run some inference in the off-hours on the machines that you already have. Could be useful for analytical tasks that don't require to be instant. On the technical side this doesn't seem that groundbreaking for me though.
pm90
My warm take is that Apple is leaving a lot of money on the table by not investing in creating an independent supply chain for their chips and building their own cloud. They arguably had the first mover advantage when it came to general purpose arm compute; all they had to do was flood the market and make it easy for anyone to rent it. Not only would they corner a part of the market but perhaps ease demand pressure on other chip manufacturers too.
gempir
Interesting, so this is basically Apple's version of exo ? https://github.com/exo-explore/exo
brandonpelfrey
I don't get it. In the paper it sounds like it's "just" a CRUD DB, then you have some fleet of Macs, and they store inputs and outputs in S3. What's the innovation here? Not trying to poo on this, but it looked like the most basic and obvious approach.
pjmlp
Apple rediscovering HPC clusters, but without OS X Server to serve alongside it.
skhameneh
I’m a bit disappointed in the lack of depth (and use of Ollama): https://arxiv.org/html/2610.12970v1 Apple has released some small models previously that seemed genuinely great, along with some quality research/efforts. I’m just not seeing the same level of depth here, am I missing something?
tw1984
internal system, so the IT/HR department is the solution to leechers. nothing new here.
djoldman
Paper: https://arxiv.org/pdf/2610.12970 Shortest promoted paper I've seen from a FAANG.
sehw
>Apple steals your electicity while you take a dump
lynndotpy
It would be so incredibly cool if we finally had an accessible consumer-accessible way to turn a network of computers on a network into a supercomputer. A household has a child who gets into 3D artwork and wants to render something? People can opt their tablets, phones, laptops, whatever to crunch out some frames overnight while not being used.
mindwork
Is this opt-in or opt-out?
eikenberry
Sounds similar to Salad (salad.com), except for the differing hardware.
magicmicah85
It's not a novel idea, but its provable that someone can take this same concept and do something truly groundbreaking. I wonder if there's value in the idea that you can join a supercomputer network of MAC/Nvidia GPUs as a way of getting off cloud and into "our cloud". As long as you offer compute, you have credit into the system to be able to support your own workloads that can't be done on just your hardware. Need to address concerns about privacy, abuse, etc, but Apple's idea here has some merit if applied right.
nico
Would love to build something like this but for classification models that run on CPU. Like a “Classify @ Home” p2p compute network, to which people could contribute their machines and see what work is being done Building the classification part now :) https://jeffyclassify.com/
bouk
Why is this a paper? Should've just been a blogpost. Maybe I don't understand academia
cmdrk
Apple has reinvented cycle scavenging about 40 years later.