PS5LM
An open-source project that ports llama.cpp to jailbroken PlayStation 5 consoles, enabling native execution of GGUF-format models.
Timeline (last 90 days)
A jailbroken PlayStation 5 can run local large language models at over 100 tokens/s.
During the jailbreak, by reallocating CPU priority, unlocking general-purpose GPU compute access, freeing additional memory bandwidth, and combining with a model fork (PS5LM) optimized for parallel processing and memory bandwidth, an inference speed of 100+ tokens/s is achieved.
The PS5LM project is a GitHub repository for running Llama.cpp on jailbroken PS5s.
All Facts (3)
A jailbroken PlayStation 5 can run local large language models at over 100 tokens/s.
50%UnverifiedDuring the jailbreak, by reallocating CPU priority, unlocking general-purpose GPU compute access, freeing additional memory bandwidth, and combining with a model fork (PS5LM) optimized for parallel processing and memory bandwidth, an inference speed of 100+ tokens/s is achieved.
50%UnverifiedThe PS5LM project is a GitHub repository for running Llama.cpp on jailbroken PS5s.
50%