{"name":"PS5LM-Plus","repo":"abhi245y/PS5LM-Plus","url":"https://midorreal.com/project/abhi245y-ps5lm-plus","repository":"https://github.com/abhi245y/PS5LM-Plus","description":"llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8","facts":{"license":{"value":"GPL-3.0","source":"https://github.com/abhi245y/PS5LM-Plus","checked":"22 Nov 2026"},"language":{"value":"C++","source":"https://github.com/abhi245y/PS5LM-Plus","checked":"22 Nov 2026"},"last_release":{"value":"v0.8.4, 17 Oct 2026","source":"https://github.com/abhi245y/PS5LM-Plus/releases","checked":"22 Nov 2026"},"releases":{"value":"11","source":"https://github.com/abhi245y/PS5LM-Plus/releases","checked":"21 Nov 2026"},"contributors":{"value":"2","source":"https://github.com/abhi245y/PS5LM-Plus/graphs/contributors","checked":"21 Nov 2026"},"archived":{"value":"no","source":"https://github.com/abhi245y/PS5LM-Plus","checked":"22 Nov 2026"}},"stars":528.0,"writeup":{"what_it_is":"PS5LM Plus is a native app that runs llama.cpp on a jailbroken PlayStation 5, using the console's GPU through ggml's Vulkan backend to run GGUF language models. It includes a dashboard on the TV, a model library and download manager, and a chat interface and OpenAI-compatible API served on the local network.","audience":"Owners of jailbroken PS5 consoles who want to run local language models","claims":[{"kind":"specific","claim":"Runs GGUF models on the console's GPU with 12 GiB of direct memory","excerpt":"A native app (a title) gets the console's 12 GiB of direct memory and the GPU","status":"not_checked"},{"kind":"specific","claim":"Qwen3.8-27B UD-Q2_K_XL generates at 20.3 tok/s at 32k context","excerpt":"Qwen3.8-27B UD-Q2_K_XL (9.2 GiB) | 32k, q4_0 cache | 20.3 tok/s","status":"not_checked"},{"kind":"specific","claim":"Llama 3.2 3B Instruct Q4_K_M generates at 124 tok/s","excerpt":"Llama 3.2 3B Instruct Q4_K_M (1.9 GiB), from USB | 64k, q8_0 cache | 124 tok/s","status":"not_checked"},{"kind":"specific","claim":"Provides OpenAI-compatible and Anthropic-compatible API endpoints on the local network","excerpt":"OpenAI Chat Completions and Responses, and Anthropic Messages, on the same port.","status":"not_checked"},{"kind":"specific","claim":"Downloads check files against their SHA-256 and resume after a dropped connection","excerpt":"a queue that survives a dropped connection, a pause and the app restarting","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-24"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":30,"reality":14,"gap":16,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-17T02:31:43+00:00","text":"Latest release v0.8.4","source":"https://github.com/abhi245y/PS5LM-Plus/releases"},{"date":"2026-10-09T19:25:42+00:00","text":"First release","source":"https://github.com/abhi245y/PS5LM-Plus/releases"},{"date":"2026-10-09T14:22:36+00:00","text":"Repository created","source":"https://github.com/abhi245y/PS5LM-Plus"}],"cite":"PS5LM-Plus is a GitHub project at https://github.com/abhi245y/PS5LM-Plus written mainly in C++, described there as \"llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8\".","attribution":"Data from Mid or Real, https://midorreal.com/project/abhi245y-ps5lm-plus, checked 22 November 2026. Attribution with a link is required.","still_real":null}