PS5LM
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
- Stars
- 204
- Forks
- 20
- + today
- +1
- Created
- 7d
Ranking data as of October 15, 2026 (UTC).
Star History
Today, hour by hour
Overview
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8 It ranks #4978 on GitTiger, gaining +1 star on October 15, 2026 (UTC).
The project is written in C++ and has 20 forks. It was created 7d ago.
What it is
PS5LM is a C++ project described as llama.cpp on a jailbroken PS5, running GGUF models natively on the console, starting with Qwen 3.8. Supplied metadata: language C++; license GPL-3.0; topics: none supplied.
Capabilities
The README summary, paraphrased, describes a native app on the console with a TV dashboard, a model catalogue, and an OpenAI-compatible API plus chat for devices on the network. It reports that a native app gets the console's GPU and memory, whereas a payload has no GPU access.
Getting started
No setup steps were supplied, so follow the README at https://github.com/abhi245y/PS5LM for installation and configuration.
Missing evidence
The supplied data does not include the jailbreak requirements, the firmware versions, or the install steps. Performance figures come from the README summary and were not checked. Topics were not supplied.
git clone https://github.com/abhi245y/PS5LM.git
cd PS5LM
# see README for setupFrequently Asked Questions
Which models are mentioned?
The description says GGUF models, starting with Qwen 3.8; the README summary includes a Qwen3.8-27B table entry.
Is there an API?
The README summary says there is an OpenAI-compatible API for every device on the network.
Which license applies?
The license field reads GPL-3.0.