llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
{ "host_memory_mib": 8192, "host_reserve_mib": 2048, "nodes": [ {"id": "ps5-a", "endpoint": "192.168.50.21:30052", "memory_mib": 10240, "reserve_mib": 2048}, {"id": "ps5-b", "endpoint": "192.168.50.22:30052", "memory_mib": 10240, "reserve_mib": 2048} ] }