PS5LM good first issues (C)

The frame loop stalls while the TV is off, so PC control requests wait 5 days ago

bug help wanted app

cobanov/PS5LM

7

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

C

#homebrew#llama-cpp#llm#playstation-5#ps5#qwen

Decision models: the server stops answering after about 55 requests on the console 5 days ago

bug help wanted gpu

cobanov/PS5LM

7

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

C

#homebrew#llama-cpp#llm#playstation-5#ps5#qwen

Downloads slow to 1-2 MB/s after ~1.4 GB: the console limits a title's writes to /data; writing through ftpsrv fixes it 9 days ago

bug help wanted app

cobanov/PS5LM

7

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

C

#homebrew#llama-cpp#llm#playstation-5#ps5#qwen

Run more models on your PS5 and report the numbers 19 days ago

documentation help wanted good first issue console

cobanov/PS5LM

7

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

C

#homebrew#llama-cpp#llm#playstation-5#ps5#qwen

GPU inference: ggml-vulkan on the PS5 Vulkan driver about 1 month ago

enhancement help wanted gpu

cobanov/PS5LM

7

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

C

#homebrew#llama-cpp#llm#playstation-5#ps5#qwen

Find the real limit for models locked in memory (1.6 GB today) about 1 month ago

enhancement help wanted console

cobanov/PS5LM

7

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

C

#homebrew#llama-cpp#llm#playstation-5#ps5#qwen

Bigger models (Qwen 3.8 27B) through a native app with direct memory about 1 month ago

enhancement help wanted console

cobanov/PS5LM

7

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

C

#homebrew#llama-cpp#llm#playstation-5#ps5#qwen

PS5LM app: pick, download and run models from one payload about 1 month ago

enhancement help wanted console app

cobanov/PS5LM

7

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

C

#homebrew#llama-cpp#llm#playstation-5#ps5#qwen

cobanov/PS5LM

Open Issues Need Help