PS5LM Plus Runs Llama.cpp Models On A Jailbroken PS5 GPU
A GitHub project called PS5LM Plus runs GGUF language models on a jailbroken PlayStation 5 and serves chat from a PC or phone on the same network. Developer abhi245y built it on PS5LM, Mert Cobanov's llama.cpp port. In the developer's measurements, Qwen3.8-27B at UD-IQ2_XXS generated 20.7 tokens per second, and Llama 3.2 3B Instruct Q4_K_M loaded from USB reached 124 tokens per second.