⬢github C++ · 582 ★ +60 since we first saw it · pushed 3 d ago · GPL-3.0
cobanov/PS5LM
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
PS5LM is a homebrew app that ports llama.cpp to a jailbroken PlayStation 5, loading GGUF models onto the console's RDNA 2 GPU via its Vulkan backend. It serves OpenAI- and Anthropic-compatible APIs to your network, runs decision models, supports vision models, and shows requests and console stats on the TV — a private, no-PC model server under your couch.
Why now: It's a novel hack — running local LLMs natively on a game console — and got attention on Hacker News as a demo of llama.cpp's flexibility on unexpected hardware.
Who it is for: Hobbyists with a jailbroken PS5 who want a self-hosted, private local LLM server at home.
homebrewllama-cppllmplaystation-5ps5qwen
Stars over our 139 snapshots: 522 to 582, since 1 d ago.
Where people talked about it
API: https://socialmediatrends-api.osmike.com/v1/repos/cobanov/PS5LM