A jailbroken PlayStation 4 can now run a modern large language model entirely offline, with no separate computer or internet connection, using a free open-source app called Garlic LLM from developer Leonardo Alegría

1

2

.

Source: TweakTown

Source: TweakTown

The model is Qwen3.5-9B, Alibaba's small open-weight model with 9 billion parameters, and it runs on console hardware from 2013.

How it fits, and how it's fast

Squeezing the model down is what makes the whole thing possible: at full precision the model is estimated to need more memory than the console's 8GB of shared memory. Alegría quantized it with mixed 3-bit and 4-bit weights, a compression method that trades some precision for size, shrinking it to about 4.5GiB

1

2

. The context window, the amount of text the model can consider at once, is cut to 16K tokens from a native 256K to keep the memory budget workable

1

.

In text chat the model produces 31 to 39 tokens per second, where a token is roughly a word fragment, and up to 43 tokens per second when generating code

1

2

. The project credits that speed to speculative decoding using Qwen3.5's multi-token prediction head, which drafts up to two tokens ahead and has the full model check them

1

2

. That matches how Alibaba trained the model.

Talking straight to the GPU

The technical trick is the route to the hardware. The PlayStation 4 has no homebrew GPU driver layer, so the developer had to write the low-level pieces from scratch

1

. Garlic LLM skips driver layers altogether

1

2

. It uses custom OpenCL C compute kernels, compiled with LLVM for the Graphics Core Next architecture in the console's Radeon GPU, plus hand-built PM4 command buffers

1

2

. Neither the standard llama.cpp tooling nor a Vulkan port is involved

1

2

.

The closest prior project is PS5LM, a fork that ran Qwen3.8-27B, a model three times larger, at around 20 tokens per second on a PlayStation 5

1

. It took a different road, though: standard llama.cpp code over a Vulkan driver port

1

.

What you need to run it

The app needs a jailbroken console running GoldHEN, a homebrew enabler; it contains no exploit itself, and installing GoldHEN is at the user's own risk. It was tested on firmware 11.52

1

2

. The download is free, 5.66GB on Hugging Face, installed through the PS4 Package Installer with about 6GB of free space needed

1

2

.

Beyond text, it handles voice conversation in seven languages using the Chatterbox speech model, and chat speed drops to about 22 tokens per second while speech runs

1

2

. Dictation runs via Nvidia's Parakeet model, which covers 25 European languages

1

2

.

The catch is that every performance figure comes from the developer's own testing and user reports, and the test prompt and method have not been published

1

2

. The developer has not tested the PlayStation 4 Pro, and the PlayStation 5 is not supported; the app targets the PlayStation 4's GPU and system software specifically

1

. The developer's website lists user-reported PlayStation 4 Pro results of up to 56 tokens per second through an experimental native mode, and he is asking owners to post their own numbers on GitHub

2

.

© 2026 TheOutpost.AI All rights reserved