{"name":"PS5LM","repo":"cobanov/PS5LM","url":"https://midorreal.com/project/cobanov-ps5lm","repository":"https://github.com/cobanov/PS5LM","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/cobanov/PS5LM","checked":"22 Nov 2026"},"language":{"value":"C++","source":"https://github.com/cobanov/PS5LM","checked":"22 Nov 2026"},"homepage":{"value":"https://ps5lm.cobanov.dev","source":"https://ps5lm.cobanov.dev","checked":"22 Nov 2026"},"last_release":{"value":"v0.11.0, 2 Nov 2026","source":"https://github.com/cobanov/PS5LM/releases","checked":"22 Nov 2026"},"releases":{"value":"7","source":"https://github.com/cobanov/PS5LM/releases","checked":"21 Nov 2026"},"contributors":{"value":"8","source":"https://github.com/cobanov/PS5LM/graphs/contributors","checked":"21 Nov 2026"},"archived":{"value":"no","source":"https://github.com/cobanov/PS5LM","checked":"22 Nov 2026"}},"stars":872.0,"writeup":{"what_it_is":"PS5LM is a project that runs llama.cpp on a jailbroken PS5, loading GGUF models onto the console's GPU and serving them over the local network through OpenAI and Anthropic compatible APIs. It also includes a TV interface and support for decision models.","audience":"Owners of jailbroken PS5 consoles who want a local model server on their network.","claims":[{"kind":"specific","claim":"Runs llama.cpp on the console's GPU using the Vulkan backend","excerpt":"llama.cpp's Vulkan backend on the console's RDNA 2 GPU, with 11.4 GB of the shared memory","status":"not_checked"},{"kind":"specific","claim":"Serves OpenAI and Anthropic compatible endpoints over the network","excerpt":"OpenAI's `/v1/chat/completions` and `/v1/responses`","status":"not_checked"},{"kind":"specific","claim":"Qwen 3.5 0.8B Q4_K_M reaches 207 tokens per second on a PS5 Slim","excerpt":"Qwen 3.5 0.8B, Q4_K_M | 0.5 GB | 207 tokens a second","status":"not_checked"},{"kind":"specific","claim":"Includes a Console page charting temperature, power and load","excerpt":"A Console page charts temperature, power, GPU and CPU load","status":"not_checked"},{"kind":"specific","claim":"Offers a decision model endpoint answering typed questions","excerpt":"the console answers TypeSafe's `/v1/systemone`","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-17"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":55,"reality":78,"gap":-22,"momentum":0.3,"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":"2026-11-02T15:40:14+00:00","text":"Latest release v0.11.0","source":"https://github.com/cobanov/PS5LM/releases"},{"date":"2026-10-02T00:29:32+00:00","text":"First release","source":"https://github.com/cobanov/PS5LM/releases"},{"date":"2026-10-01T21:09:59+00:00","text":"Repository created","source":"https://github.com/cobanov/PS5LM"}],"cite":"PS5LM is a GitHub project at https://github.com/cobanov/PS5LM 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/cobanov-ps5lm, checked 22 November 2026. Attribution with a link is required.","still_real":null}