Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console
Points and comments are a snapshot, not live.
Article body wasn't reachable. The HN discussion summary is below.
Points and comments are a snapshot, not live.
Article body wasn't reachable. The HN discussion summary is below.
What commenters are saying
Commenters said the project uses the PS5's 11.4 GB of shared memory, making it useful for those without a GPU. The model tested is Qwen 3.8 27b at a 2-bit quant, which is noticeably worse than 4-bit. Performance is slower and less capable than proprietary models like Opus 4.6 or GPT-4. Some argued the PS5 is sold at a profit, so Sony likely won't target this project. Others debated hosting on GitHub due to takedown risk, suggesting torrents or self-hosted git as alternatives.