HN

Need help?
<- Back
Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console

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

Anon84

Comments (41)

  • Rabbit504030201
    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.
  • jjcm
    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 wateringetc. 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).
  • xnx
    I've never even considered getting a PS5, but hackers converting a locked-down appliance into a general purpose computer has me really considering.
  • shiftpgdn
    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.
  • pwython
    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.
  • tombot
    2026 is a weird time, llms on a ps5
  • kevmo314
    Not long until Anthropic's dreams of self-replicating models starts taking over PS5s!
  • hypfer
    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.
  • randomblock1
  • drewg123
    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..?
  • anon
    undefined
  • Kurtz79
    Don't give Sony ideas...
  • ThrowawayTestr
    11.4G of shared memory. Could do something interesting if you don't have a GPU.
  • armcat
    The toaster is next!