Yet another Hacker News

Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console

298 points Anon84 16 hours ago 74 comments

ThrowawayTestr 16 hours ago | parent

11.4G of shared memory. Could do something interesting if you don't have a GPU.

kevmo314 16 hours ago | parent

Not long until Anthropic's dreams of self-replicating models starts taking over PS5s!

crorella 15 hours ago | parent

Haha, I was thinking the same, I think we will see the most random devices being able to host models in the near future. An army for the techno core.

Kurtz79 16 hours ago | parent

Don't give Sony ideas...

randomblock1 15 hours ago | parent

Relevant: https://en.wikipedia.org/wiki/PlayStation_3_cluster

russellbeattie 15 hours ago | parent

Obligatory... "Can you imagine a Beowulf cluster of these?"

Anon84 15 hours ago | parent

Those were relatively big for scientific computing in the PS2 days

https://www.ncsa.illinois.edu/2003/05/27/playing-the-superco...

armcat 15 hours ago | parent

The toaster is next!

pwython 15 hours ago | parent

With this in mind, having LLM-powered NPCs would be a beautiful thing. There's been limited testing on PC games (PUBG Ally), but I can imagine it will be the standard.

tiahura 14 hours ago | parent

Fortnite Darth Vader already did

greggsy 13 hours ago | parent

After all of the agonising about AI companions, we realised that we just wanted someone to play games with.

drewg123 15 hours ago | parent

For somebody who hasn't kept up with all the different open source models and what token rates mean, how would using this compare to something like codex or claude? I assume it would be much slower and less capable..?

robotswantdata 14 hours ago | parent

Significantly slower and less capable than opus 5.5

However you can run comparable or better models than gpt4. Try to stay under 30b

system2 13 hours ago | parent

GPT-4 and Opus 4.8 were the models that started the AI craze. Now people look down on them.

kadoban 7 hours ago | parent

Qwen 3.8 27b is a great model, but 2 bit quant of it is _not_ Opus 4.8 level.

kadoban 7 hours ago | parent

The model they're running is Qwen 3.8 27b. It's maybe somewhere around Opus 4.6 level, it's quite good. I didn't check the benchmarks, that's from memory/vibes.

The ~issue is though that they're using a pretty low quant, 2 bit. 4 bit are _pretty_ close to full ability, maybe degraded a bit. 2 bit is _noticably_ worse. It's about as small of a quant as you can get while still pretending it works, for this model.

This won't replace claude for you, unless you baby it a lot and are okay with it being kind or derpy.

thombles 7 hours ago | parent

Qwen3.8-27B is surprisingly effective, somewhere in the vicinity of Opus 4.6, but it needs to do a lot of inference-time computation. i.e. anything moderately involved requires xhigh reasoning and it will spend literally tens of thousands of tokens turning over a problem before emitting the answer. The answer/code/whatever is often surprisingly good, but if you’re in the low tens of tok/s you’ll be waiting a long time to get it.

As sibling said, you won’t hit the same quality using a 2 bit quant like this project, which is unfortunate but that’s the reality today.

Rabbit504030201 15 hours ago | parent

The project's primary site should not be GitHub, and I am serious. Playstation 5 is not some historical curiosity and Sony might strike the page down any hour now.

Those projects should default to hosts less geared toward corporate governancy; custom internet domain being the first requirement.

Retr0id 14 hours ago | parent

I'm sure Sony has an opinion of the jailbreaks that enable this, but they really don't give a shit about anyone running llama.cpp. Why would they? They're just glad you're not pirating games.

xp84 14 hours ago | parent

Is there a real or imagined hardware subsidy on the PS5 hardware though? In other words, is the current MSRP below what Sony would charge in a hypothetical world where they weren’t involved in any form of gaming software business, with an assumption that they will make additional margin dollars from game sales? I can see some manager making the case that repurposing the hardware for non-gaming use is taking food off his family’s table, in a manner of speaking. If so, it’s an argument that you don’t want this type of use to become popular and have PS5s start flying off shelves and never having games bought for them.

sourweasel 9 hours ago | parent

The PS5 hardware is essentially identical to the AMD BC-250 mining rig, with the major difference being that the media engine (VCN for encoding/decoding video) is disabled in the miner because it requires Sony's proprietary bios. The BC-250 was created from binned chips that didn't meet Sony's specs and had 2 of 8 cores disabled, but many users successfully re-enabled them and bumped active CUs on the GPU from 24 to 40.

To your point, it was briefly possible to buy them for under $100 until word spread that they make decent steam machines, so I'm guessing that Sony doesn't need to sell any games to turn a profit. Even at their current prices it would be far cheaper to use the BC-250 for local inference.

rlpb 3 hours ago | parent

> To your point, it was briefly possible to buy them for under $100 until word spread that they make decent steam machines, so I'm guessing that Sony doesn't need to sell any games to turn a profit.

I don't follow your logic. If the BC-250 was made from PS5 quality control failures, then why would their pricing have any bearing on the PS5's profitability, except as an effort to increase margins? Does cost not remain independent of pricing?

As far as I cam infer from what you said, it could be that the PS5 was sold at a loss and still is even with the BC-250 helping, or that it was sold at a profit and is still is with the BC-250 helping. What am I missing?

gunalx 2 hours ago | parent

No it implies that å ps5 hardware wise wouldnt be ordets of magnitude of å bc250 to produce, and it therefore probably dosent have negative margins at least.

tancop 3 hours ago | parent

There is no hardware subsidy in the traditional sense. The last time Sony was selling consoles at a loss was the fat PS3 and they learned their lesson from all the compute clusters. Every PS5 is sold at a profit.

The only way they can lose money is if their existing users stop buying games and that's not happening yet. Maybe when vibe coded community servers for online games get better and everyone jailbreaks their console because they don't have to worry about getting banned.

But even with that every unit sold is a net positive for them because they make money off the sale, and if they run out they can use it to justify higher prices.

minimaxir 14 hours ago | parent

There's no feasible way to avoid takedowns/DMCA in 2026 unless you do TOR shenanigans. Even with a custom domain, Sony could just DMCA the web host for the project.

kevmo314 14 hours ago | parent

Sure you can. This repo has definitely been vacuumed into the latest training data dump, so the next generation of models will happily spit out a similar reproduction, Sony be damned!

perching_aix 11 hours ago | parent

We got immortalization at home.

nekusar 14 hours ago | parent

Gitflic.ru begs to differ.

haunter 14 hours ago | parent

Magnet link, once the DHT networks picks it up (and there are seeders) no one will take it down unless they go after every single IP address

toomuchtodo 9 hours ago | parent

Any recommendations for code that’ll one shot pull a GitHub repo zip from an repo url and announce and seed a magnet torrent?

Looking for similar UX to https://archive.softwareheritage.org/save/ (which archives an source control repo on demand from a url, but is still a single point of failure)

pdntspa 8 hours ago | parent

Seems like something Opus could author in a few minutes given the right credentials

toomuchtodo 8 hours ago | parent

Asking is free before I have Claude grind.

2III7 14 hours ago | parent

Torrents. Got the leaked GTA6 videos by torrenting and they're still easily available on public trackers. Don't see why projects like these couldn't be distributed similarly if shit hits the fan.

agoodusername63 11 hours ago | parent

There are several public git hosts hosted in countries that don't care about DMCA.

And nothing is stopping you from renting a VPS from a provider based in that country and running gitlab or something.

The worst part is sharing around a sketchy URL but, that just comes with the territory when you're in the DMCA dodging parts of the internet.

Computer0 9 hours ago | parent

What are they named?

Mindwipe 46 minutes ago | parent

There are not.

Renting a VPS from a country that genuinely doesn't is pretty risky for numerous reasons, least of all international sanctions.

bubbluppugus 10 hours ago | parent

git is a distributed protocol that does not demand distribution happen through github.com

Private keys and private endpoints is all we need

neuronexmachina 9 hours ago | parent

There's also something like radicle: https://radicle.dev/

>Radicle is an open source, peer-to-peer code collaboration stack built on Git. Unlike centralized code hosting platforms, there is no single entity controlling the network. Repositories are replicated across peers in a decentralized manner, and users are in full control of their data and workflow.

LoganDark 14 hours ago | parent

> Those projects should default to hosts less geared toward corporate governancy; custom internet domain being the first requirement.

I struggle to think of anywhere on the entire open internet you could put something like this where it could not be taken down.

mindslight 9 hours ago | parent

It'd be kind of interesting if someone started a public git host whose main value add was being judgement proof, like Anna's Archive, torrent sites, etc. The methods exist, it's just a matter of implementation and getting a critical mass. Obviously TOR-hidden-service first, but then making it available to naive hidden browsers would be its own public service.

I hate the centralization of centralized git watering holes, but it is what it is. And frankly getting older and not as able to keep up, having all the cool projects in one place would massively help my street cred.

jrm4 9 hours ago | parent

I'm still waiting for people to figure out that Git needs no "hub" at all.

dewey 2 hours ago | parent

The "but don't you know git is distributed" commentary always sounds clever, but it really isn't.

GitHub isn't just used to host your actual git work tree and everyone knows that, it's an issue tracker, an easy way for projects to get contributions as everyone already has a GitHub account, an easy way to receive bug reports, CI, a website for your project, a popularity metric like GitHub stars (For better or worse).

anigbrowl 7 hours ago | parent

Maybe so, but the Github page isn't hosting or instructing anyone to jailbreak their PS5, which in any case would be a civil matter. They're just telling you what you can do with the hardware. I'm gonna guess you could just run it on a BC-250, although this wouldn't be as aesthetically pleasing to look at as the PS5.

dewey 2 hours ago | parent

That's exactly why you put it on GitHub, which is the most visible place so people will mirror, check it out locally etc.

xyzsparetimexyz 2 hours ago | parent

Who gives a shit that it could be taken down??

shiftpgdn 14 hours ago | parent

Conceivably this should also work on the BC250 cards, which are ex-cryptocurrency mining motherboard built around AMD's "Cyan Skillfish" APU which is a cut-down version of the PlayStation 5's custom silicon. You can still pick them up on ebay for $150-$200.

haunter 14 hours ago | parent

Good luck finding one for $150 or even for $200

And at that price point or a little bit more you might as well just get an RTX 3060 and save yourself a lot of hassle (you also get DLSS, DLAA etc.)

shiftpgdn 14 hours ago | parent

I paid $150 shipped a few months ago then maybe $40-50 for all the parts to run it. The RTX 3060 sells for $400+ in my market and still needs a computer to attach it to!

LoganDark 14 hours ago | parent

Just opened up eBay and they're going for like $200 here, $220 if you want a "modded BIOS" (whatever that means).

greggsy 14 hours ago | parent

Flashing the bios takes ten minutes with a thumb drive. It’s hard to get wrong but guess some people would be nervous enough about that to pay $20 extra.

LoganDark 12 hours ago | parent

I also figure the seller was just lazy to change it back.

xnx 14 hours ago | parent

I've never even considered getting a PS5, but hackers converting a locked-down appliance into a general purpose computer has me really considering.

stuxnet79 14 hours ago | parent

Well that locked-down appliance is way under-specced compared to an equivalent build at the same price.

throwaway240403 13 hours ago | parent

Does that remain true in the RAMpocalypse?

nvme0n1p1 13 hours ago | parent

A PS5 is $600. This random mini PC with the same amount of RAM is $385. https://www.bee-link.com/products/beelink-eq14-n150

I'm sure someone will point out some spec that's better on the PS5, but the extra $200 will make up the difference if you spend more time looking than the 15 seconds I just did.

(or if you just build a PC from parts yourself)

p1necone 12 hours ago | parent

>I'm sure someone will point out some spec that's better on the PS5

They're not even in the same ballpark - the PS5 is more than an order of magnitude better in GPU performance.

Despite how much it does matter, RAM is not the only thing you need for running LLMs - that N150 is not going to run anything but really tiny models at any sort of reasonable speed - certainly nothing that approaches using all of its ram. The GPU in the PS5 is ~25x faster. And if you're running games the RAM doesn't really affect performance at all once you have "enough" for a given game.

You're right that you probably could build something quite a bit faster than a PS5 for the same price though - if you can build/find everything but the GPU for ~250 USD and slap a 16gb 9060xt (~25tflops @32bit compared to the PS5 gpus ~10tflops @32bit) in it for another ~350 USD it should theoretically do a better job - the GPU in the PS5 was on par with mid-high end PC GPUs on launch, but that was like 5 years ago.

kennywinker 12 hours ago | parent

Where are you getting a 16gb 9060xt in 2026 for $350? Unless you mean used, seems like the floor is $500

p1necone 3 hours ago | parent

That'll teach me for trusting pricing information from Google ai summaries...

yathern 12 hours ago | parent

N150 isn't really what you'd want to use for a gaming machine. At a budget of mid $300s - the best (new) Mini PC you're going to find right now is probably this unit[1] with a Ryzen 7 7735U (680M iGPU) and 16GB RAM. Not the most powerful device - but I have a similar one I use to play emulator games, indie games on steam - throw Steam OS on it and it's a great living room device. Expand that budget to $530 and you can get this guy[2] with a Ryzen 7 255 (780M iGPU) - which will play modern games (on low settings for many).

[1] https://www.amazon.com/dp/B0GGM6BKN9 [2] https://www.amazon.com/dp/B0FX2TV3HX

Shameless plug - I methodically rank the best possible Mini PC deals on https://MiniPCs.zip for this exact purpose.

poglet 10 hours ago | parent

Any chance it could include Amazon, eBay from Australian region + AliExpress ? Great website. Also is source available?

agoodusername63 11 hours ago | parent

your miniPC doesn't have GDDR RAM. PS5 does!

kcb 10 hours ago | parent

An N150 for $385 is a joke.

madduci 5 hours ago | parent

These prices are from last year. A new N150 without RAM costs €350. and performance-wise, a N150 is far behind to a PS5, which costs €799.

gambiting 13 hours ago | parent

Even at the current increased prices - you can build a PC with a better spec and with a 4K Blu ray drive for £569? I'd be curious how.

jeroenhd 20 minutes ago | parent

A second hand PS5 with about 12GiB of usable RAM is cheaper than the equivalent amount of RAM if bought new.

Ever since RAM prices grew 6x, these old appliances suddenly became a lot better value for money.

Tools like these will probably just spike the prices of second hand PS5s though.

thenthenthen 9 hours ago | parent

Check out the BC-250 boards, basically reject ps5 apu’s being repurposed for all kinds of shenanigans

pdntspa 8 hours ago | parent

It's been a little bit since any major hacks have hit the news but this is a time honored tradition partcularly with the Playstation. Way back when the PS3 arrived the US government was considering export sanctions because they were too powerful. I believe some universities even kept a cluster of PS3s for their distibuted computing courses or for research. Sony even had an approved way to run Linux.

numpad0 3 hours ago | parent

PS5 at $650 MSRP is actually the same price as cheapest new AMD GPUs with the same VRAM capacity.

hypfer 13 hours ago | parent

Kinda cool but also entirely useless given the limited VRAM.

The readme oversells it by pretending it would be something actually usable, when instead it is a cool achievement to make it happen.

none_to_remain 13 hours ago | parent

A 20 tps Qwen3.8-27B at 2 bits quantization is limited but not useless. I've been putting one on "read this codebase and figure out XYZ" for me, where the typos are less consequential.

jjcm 13 hours ago | parent

Even though it only runs qwen 3.8 27b at a 2 bit quant, it's still highly viable, especially for things where you just need a constant token stream of slightly below average intelligence, ie this would be great for things like:

- monitoring server error rates

- reviewing security footage

- watching plant growth / controlling watering

etc. Any long running task you can now just slap a PS5 on it. 70 cents a day in power cost means you now get ~2M output tokens per day (~$3.50 worth of usage). It's not the worst thing in the world if you have one lying around. 2bit isn't even that terrible - it's ~80% the accuracy of 27b at full quant, which should put it at around GPT-5 levels of intelligence (which honestly is crazy in its own right).

nicklam901 5 hours ago | parent

Wonder if there is an advantage to chain multiple PS5 with this and spread the load over, or just have it stand by for an orchestrator to use it for those tasks across. Cost definitely comes in a good factor, especially leaving it just sitting at home.

tombot 12 hours ago | parent

2026 is a weird time, llms on a ps5

ra0x3 7 hours ago | parent

Stupid question. Can I still play my video games if I use this?