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

A jailbroken PlayStation 5 can natively run any GGUF model using Llama.cpp, turning the console into a language model server for all network devices. Performance varies by model size; for instance, a PS5 Slim can process Qwen 3.5 0.8B at 207 tokens/second, Qwen 3.5 9B at 55 tokens/second, and Qwen 3.8 27B at approximately 20 tokens/second with a 64k context. A d1 Omni 600M decision model can answer 3 questions in 0.3 seconds.

This report details the first instance of a jailbroken PS5 natively running GGUF models via Llama.cpp, unlike previous methods that required more specialized hardware.