YHK - yet another hacker news clone

Nvidia RTX Spark encrypted firmware slows inference speed to 35% on Linux

88 points novaRom 2 hours ago 45 comments

rich_sasha 1 hour ago | parent

This one is allegedly/hopefully a bug but just waiting for it to become a revenue stream / paywall. Uh oh, you want to run locally your dangerous illegal foreign open models, not licensed by Nvidia? Can’t work with you paying for a special security feature unlock on your GPU.

Or maybe just not at all - shell out for OAI tokens and send us all your data - your privacy is very valuable to us and we will make sure to be the only ones to monetize it.

You could say, Nvidia is selling pickaxes and has no business gatekeeping what rocks you hit with it, but I guess it depends on their relationships with major mining companies, and ultimately what pays more.

hypfer 1 hour ago | parent

Why does the title say DGX spark when the link is the RTX Spark laptop?

Those are very different things as far as I understand, and the whole "doesn't work well with linux" really only makes sense on the RTX Spark laptop I think? Isn't the DGX spark linux by default?

novaRom 43 minutes ago | parent

Good point, fixed, thanks.

schaefer 1 hour ago | parent

The article is about the RTX Spark, not the DGX Spark. The title should be changed.

sampo 1 hour ago | parent

Looks like the site has fixed the title.

fxwin 1 hour ago | parent

> A hands-on look at dual-booting Linux on the Nvidia RTX Spark laptop, the GPU clock throttling bug found, and why WSL still wins.

Man it really is exhausting to read a title that sparks my interest, just to be greeted with the most basic Claude-isms in the subheading.

aa-jv 1 hour ago | parent

> sparks my interest

I see what you did there. ;)

teiferer 8 minutes ago | parent

Enumerating 3 things really ..sparks a comment nowadays? Doing that as a rhetorical device has been a thing for generations and of course LLMs mimic it because it is everywhere in their training data.

I just heard a quick J. Talarico speech at some country concert. In the 10 or so sentences he spoke, he had 3 or 4 instances of doing this "Claudism" enumeration. Are you saying Texas just elected Claude for Senate?

Maybe we should stop with such superficial judgements. It's the modern equivalent of not liking the speaker's tie. (Doesn't mean the speaker's speech is good, but it doesn't mean it's bad either.)

aa-jv 1 hour ago | parent

As a DGX Spark user, this article title gave me conniptions.

But, on the other hand, having my DGX Spark stack at hand, I know the solution:

    /btw reverse engineer the Nvidia Platform Controllers and Framework component and build a Linux version
"AI views proprietary components as damage and routes around them."

u1hcw9nx 1 hour ago | parent

Do you know that 1 + 1 = 10 in binary?

aa-jv 45 minutes ago | parent

I know that, because I read the article, but if all I'd read was the title, I'd not know that.

K0balt 1 hour ago | parent

The attack on reverse engineering of games is a precursor to universal computing lockdown. When you need AI to keep up with programming, the entity controlling the AI controls what software is possible to create. It’s a bid for centralised control and thought censorship at a scale and depth much more ambitious than anything we have ever seen before.

Sovereign AI has never been more important.

barrkel 1 hour ago | parent

I remain puzzled why anyone would want to do inference on a laptop if they have a home internet connection and a phone.

If you really want to do DIY inference, plug it in at home and set up tailscale so you can access it on the go.

No huge battery drain or toasty hot laptop required. Lower cost laptop. Lighter laptop. Longer battery life laptop. Win win win win.

solyin 57 minutes ago | parent

Not everyone grew up in a situation where home was a stable dependable place. Not everyone has a home to go to. If you have it with you, they can't mess with it or take it away from you when you're not there. If you grew up in a broken home, you would understand.

Gigachad 33 minutes ago | parent

And those people are buying $10k laptops to run local AI?

jeroenhd 25 minutes ago | parent

Those people won't be buying the Spark laptop, but asking "why anyone would want to do inference on a laptop" is broader than what the article covers.

Danox 11 minutes ago | parent

The spark laptop in its present form is not very good, in fact, it’s disappointing.

pixelpoet 56 minutes ago | parent

I have been saying this for years, and the answer hits a nerve that gets you downvoted into oblivion: people prefer the aesthetics of laptops, simple as that. They will absolutely go to the grave arguing that they need the mobility etc, then just leave it plugged in. They simply prefer how laptops look, and they absolutely hate it when someone dares say it.

monegator 31 minutes ago | parent

I have a laptop for work. 95% of the time i'd prefer a tower or at least a mini PC with proper cooling, but that remaining 5% i have to be around with the laptop is enough. I don't like the idea of having to remember to sync the projects every time (especially while i'm in the middle of testing something new so it's not like i can just pull the latest commit or sync the latest good version of something)

dlahoda 34 minutes ago | parent

private memory.

unique local data and know how not shared with cloud.

close04 15 minutes ago | parent

> why anyone would want to do inference on a laptop

Because reviewers tell them this is is a good use case, and people want to take advantage of the HW they buy [0]. Unfortunately those reviewers didn't take any extra step to validate anything beyond the default config, out of the box.

[0] https://arstechnica.com/reviews/2026/10/the-surface-laptop-u...

KeplerBoy 9 minutes ago | parent

The RTX Spark is also sold in a mac mini form factor. That's pretty well suited for home inference.

K0balt 1 hour ago | parent

Wtf. Are we actually seeing a push towards being 100percent dependent on the cloud?

Sovereign AI has never been more important.

Controlling AI is so much more powerful and impactful than controlling search or social algorithms.

Centralized AI a 10x on social control over everything we have seen before, and there is no way that a free and open society survives contact with centralised, high capability AI if the system is manipulated towards guiding outcomes. It’s essentially mind control, as people will offload an even greater share of their cognition to AI than they do with search and social.

Build and maintain sovereign AI while you still can.

InsidiousWombat 1 hour ago | parent

NVIDIA probably already figured out that local will be massive part and are preparing to do DRM for AI.

Pay up for license to unlock full capacity, pay up for license to use encrypted models from AI moguls, paid per billion tokens processed or just operations in GPU

hhh 57 minutes ago | parent

There is already DRM for AI. check out nvidia’s docs around hosting proprietary models with encrypted weights

novaRom 19 minutes ago | parent

Interestingly it is Microsoft who filed a patent for DRM-style locking of AI models to verified devices (published July 2026): https://patentlyze.com/patent/microsoft-drm-ai-models-explai...

sva_ 49 minutes ago | parent

It wouldn't work on windows either, if that were the case. It sounds more like it hasn't been properly implemented yet

AlAjem 36 minutes ago | parent

I don't see the case for DRM protected local models on either side.

The consumer has access to free and open models for local use.

The supplier has better control and wider market to serve running the models in data centers.

Only way I can see encrypted models being widespread is if they are bundled as part of a software package (OS/Browser/etc) and not sold as the product.

petu 28 minutes ago | parent

There's good open weight models for now, labs could stop releasing them for whatever reason (assuming "good model" is a moving target).

motbus3 14 minutes ago | parent

Years ago I would think I was being paranoid to think they would patch hardware retroactively to make it slower so you need to pay more to use your own hardware. In 2026, I think this is what all car companies are doing after you pay the full car price. I don't see a reason why they wouldn't do it with so little competition

sva_ 1 hour ago | parent

It should be possible to reverse engineer this, if it works on windows?

> The laptops also support unified memory configurations up to 128GB, shared between CPU and GPU, which is unusual for a laptop and central to why they’re being marketed at AI developers in the first place.

This isn't rare on laptops, pretty default on AMD with iGPU

jcarrano 42 minutes ago | parent

I though the same, reverse engineer with AI. Even run the AI on the laptop and have it reverse-engineer itself.

jleask 54 minutes ago | parent

Nvidia doing what Nvidia has always done; proprietary closed drivers. Weird choice to cryptographically protect the power settings. Key problem is that we've allowed a company that's always been this way to form a monopoly. Other brands exist, perhaps it is now worth the effort to migrate and rebuild elsewhere.

TobiasJacob 49 minutes ago | parent

Wtf is Nvidia doing?! I was considering buying one, but now?

meta-level 23 minutes ago | parent

You're not supposed to want to buy one (https://www.osnews.com/story/146277/sam-altman-wants-to-take...)

impossiblefork 44 minutes ago | parent

Unrelated to this slowdown, I could imagine this sort of thing being the right application for things like Taalas, although I'm not quite sure whether it can actually offer what I imagine that it can (i.e. ability to make a cheap, physically small card that can run a large model).

A laptop can't run the latest big models, because memory is too expensive. This thing probably can't run models larger than Mistral Small 4. But it'd be a completely different thing to have a hardcoded Mistral Large 4, than a choice of tiny models.

RealityVoid 30 minutes ago | parent

You probably won't be able to run a sota model on a single Talaas card. You probably need a set. It should theoretically be cheaper, faster, more power efficient than Nvidia at running that model. But then you are stuck with a chip that can run only that model. And I understand that context size will also be a problem.

impossiblefork 20 minutes ago | parent

Yeah, that was why I felt that, while Taalas might not be the right thing in general, it could be really appealing in a laptop, that would otherwise not be able to run any big model at all.

I think I misunderstood what the technology could do a little bit, because I imagined these fixed matrix multiplies encoded into hardware as small-ish, as using routing space etc., not just fast.

I think what I really imagined was useful would be more easily achieved by having a big ROM with model weights connected to an ordinary GPU.

ChiliPie 32 minutes ago | parent

Have you tried lact to increase clock/power level? https://flathub.org/en/apps/io.github.ilya_zlobintsev.LACT

viraptor 31 minutes ago | parent

Fortunately that's just a matter of weeks until someone revengs and publishes the fix... even if we need to wait a while for a proper upstreamed solution.

OsrsNeedsf2P 6 minutes ago | parent

As someone who went down the rabbit hole of local AI, there is so much exhausting debugging already. Even if this is "just" another step you have to find, it's toxic.

yieldcrv 29 minutes ago | parent

Decompile time

wewewedxfgdf 22 minutes ago | parent

Remember when Apple was slowing down iPhones, the outrage!

But with Nvidia people just expect they nerf all the features.