abhi245y Says PS5LM Plus Runs Qwen 3.8 27B on a Jailbroken PS5 GPU
Summary
A fork of PS5LM called PS5LM Plus runs llama.cpp on a jailbroken PlayStation 5's GPU, developer abhi245y says, loading GGUF models such as Qwen 3.8 27B at about 20 tokens per second inside an 11.44 GiB heap. It also serves an OpenAI-compatible API and chat UI over the network.
Key Points
- The fork's README credits Mert Cobanov with creating the original PS5LM, its llama.cpp port and payload.
- The README says Gemma 4 E4B QAT q4_0 loads from USB and generates 61 tokens per second.
- The README says the app restarts itself for each model switch, since unloading in place holds about 5 GiB of the pool.