llama.cpp on a jailbroken PlayStation 5, on its GPU
Running Qwen3.8-27B UD-Q2_K_XL 20.3 tok/s I think is beautiful to run a llm on a ps5!
https://github.com/abhi245y/PS5LMOpen linkView original on lemmy.mlSyndicated from the fediverse. Read and engage on the original instance.
View original on lemmy.mlhttps://github.com/abhi245y/PS5LMOpen linkView original on lemmy.ml
1 reply
i wonder if it would be better to use bonsai-2 over a regular 2-bit quant 🤔