Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console
https://github.com/cobanov/PS5LM📌 有人把 PS5 改裝成區域網路的私人 LLM 伺服器
TL;DR：開源專案 PS5LM 讓一臺破解過的 PS5 跑 llama.cpp，變成全家共用、不用雲端的推理伺服器。
你家的 PS5 在不玩遊戲的時候,GPU 其實是閒置的。有人想到一個點子：既然 llama.cpp 能跑在各種 GPU 上,為什麼不讓它跑在客廳電視下的那臺主機裡?PS5LM 這個 GitHub 專案把這個念頭變成了真的可用的東西。
🤔 想要一臺不用雲端、不用帳號的私人模型伺服器
PS5LM 的目標使用者很明確：擁有破解版 PS5、想要在家架一臺私人模型伺服器的人。它把 GGUF 模型載入主機的 GPU，提供服務給筆電、手機與各種程式開發工具使用，整個過程不需要額外的 PC、不需要雲端、也不需要帳號。
🧩 用 llama.cpp 的 Vulkan backend 吃滿主機 GPU
核心架構是 llama.cpp 的 Vulkan backend，跑在 PS5 的 RDNA 2 GPU 上，用共享記憶體裡的 11.4 GB 空間存放模型與 context，llama.cpp 支援的每一種架構與量化格式都能直接搭配使用。
對外服務的部分做得相當完整：
- 相容 OpenAI 的
/v1/chat/completions與 Anthropic 的/v1/messages（Claude Code 可以直接指向它），外加一個瀏覽器內建的聊天頁面。只要把用戶端指向http://<console>:8081,帶任何模型名稱,載入中的模型就會回應。 - 支援決策模型（decision models），透過與 Ollaya 相同的
/v1/systemoneAPI，載入像 d1、Clef、OpenJev 這類模型後,可以回傳帶校準機率的分類結果、分數或是非題答案,而不是生成文字。 - 具備視覺能力：搭配 Gemma 4、MiniCPM-V、d1 這類有影像投影層的模型,可以在聊天與決策任務中直接吃圖片輸入。
- 介面本身投影在電視上,每一個請求都會以聊天形式即時串流顯示：哪個裝置發出請求、問了什麼、回答逐字跳出。按下 Square 可以送出示範請求,Triangle 則打開鍵盤輸入,整套體驗是設計給「坐在沙發上操作」的場景。
- 內建 Console 監控頁面,顯示過去兩分鐘或一小時的溫度、功耗、GPU 與 CPU 使用率曲線。
- 模型管理上有自動規劃機制：讀取每個 GGUF 檔案,依照剩餘記憶體配置最長的 context 與最佳的 cache,並提供一份在主機上實測過的建議模型清單,可直接從 Hugging Face 下載到內部儲存、M.2 硬碟或 USB 隨身碟。
📊 幾組官方實測的推理速度
README 公布的 benchmark 數字如下：
| 模型 | 大小 | PS5 Slim 上的表現 |
|---|---|---|
| Qwen 3.5 0.8B, Q4_K_M | 0.5 GB | 每秒 207 tokens |
| Qwen 3.5 9B, Q4_K_M | 5.3 GB | 每秒 55 tokens |
| Qwen 3.8 27B, UD-Q2_K_XL | 9.2 GB | 約每秒 20 tokens，64k context |
| d1 Omni 600M（決策模型） | 1.1 GB | 3 個問題 0.3 秒；一張 720p 圖加 7 個問題 2.9 秒 |
🧩 怎麼跑起來
前提是一臺韌體版本在 7.00 到 13.60 之間、已破解的 PS5，並安裝 kstuff-lite、etaHEN、ShadowMountPlus 三個必要的 payload（分別負責核心修補、homebrew 支援、把 PS5LM 加到主畫面），elfldr 與 ftpsrv 則是建議安裝，用於溫度監控與透過 FTP 安裝模型。安裝流程是下載發布包、透過 FTP 複製資料夾到 /data/homebrew，之後就能從主畫面啟動，到 Models > Suggested 下載模型，或自行把 .gguf 檔案丟進模型資料夾。整套操作用搖桿完成：D-pad 選單、Cross 載入、Square/Triangle 送出示範或打字。
⚠️ 這終究是一個小眾的 homebrew 玩具
專案本身採 GPL-3.0-or-later，依賴的 llama.cpp 保留 MIT 授權，字體 Manrope 用 OFL。README 特別聲明不包含任何 Sony SDK 檔案、金鑰、韌體或模型權重，且專案與 Sony Interactive Entertainment 無任何關係。要玩這個東西，前提是你已經接受了破解主機的風險與法律灰色地帶，這注定只適合願意動手的 homebrew 愛好者，而非一般企業部署場景。
🎯 實務啟示
拋開「拿 PS5 跑 AI」的噱頭,這個專案真正展示的是 llama.cpp 生態的可移植性有多強：只要有 Vulkan backend 與足夠的記憶體,幾乎任何消費級 GPU 裝置都能被改裝成本地推理節點,而且決策模型的 /v1/systemone API 也證明小型、校準過機率輸出的模型同樣能在邊緣硬體上即時運作。對做邊緣推理或自架模型伺服器的工程師來說,這是個有趣的設計參考案例。
🔗 來源
- 標題：Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console
- 連結：https://github.com/cobanov/PS5LM
#PS5 #LlamaCpp #LocalLLM #GGUF #EdgeAI #Homebrew #Jailbreak #SelfHosted #OpenSource #AIHardware
原始資料 Hacker News · 收集於 2026-10-17
摘要原文
PS5LM Your PS5 runs the language model. Every device on your network uses it. llama.cpp on the console's GPU, with OpenAI and Anthropic APIs and a screen made for the TV. Get the app · Website · Get started · Issues New: decision models, powered by Ollaya . PS5LM now runs Jev-like decision models (d1, Clef, OpenJev and more) on the GPU and answers the same /v1/systemone API as Ollaya: typed decisions with calibrated probabilities, in a fraction of a second. PS5LM is for anyone with a jailbroken PS5 who wants a private model server at home. It loads a GGUF model onto the console's GPU and serves it to your laptop, your phone and your coding tools. It needs no PC while it runs, no cloud and no account. Qwen 3.5 9B answering requests from a laptop on a PS5 Slim. Click for the video. Home, Models, Console, API and Settings on the TV. A model server under your TV It runs on the GPU. llama.cpp's Vulkan backend on the console's RDNA 2 GPU, with 11.4 GB of the shared memory for the model and its context. Every architecture and quantization llama.cpp knows comes along. It answers your network. OpenAI's /v1/chat/completions , Anthropic's /v1/messages (Claude Code works against it) and a chat page in any browser. Point a client at http://<console>:8081 and use any model name: the loaded one answers. It decides, too. Load a decision model and the console answers TypeSafe's /v1/systemone : choice, score and yes-or-no questions about text and images, the API Ollaya serves on a PC. It shows its work. Every request streams across the TV as a chat: which device asked, what it asked, and the reply as it is written. Square sends a demo and Triangle opens a keyboard, so the console can be tried from the couch. It watches the console. A Console page charts temperature, power, GPU and CPU load over the last two minutes or the last hour, beside a table of every reading. It picks what fits. The planner reads each GGUF and gives it the longest context and best cache that fit the memory free. A Suggested list holds models measured on the console, and the app downloads from Hugging Face by itself, to internal storage, the M.2 drive or a USB drive. It reads images. Models with an image projector (Gemma 4, MiniCPM-V, d1) take pictures in chat and in decisions. Model Size On a PS5 Slim Qwen 3.5 0.8B, Q4_K_M 0.5 GB 207 tokens a second Qwen 3.5 9B, Q4_K_M 5.3 GB 55 tokens a second Qwen 3.8 27B, UD-Q2_K_XL 9.2 GB about 20 tokens a second, 64k context d1 Omni 600M, a decision model 1.1 GB 3 questions in 0.3 s; a 720p image and 7 questions in 2.9 s Decision models, powered by Ollaya Ollaya runs open decision models on a PC the way Ollama runs language models. PS5LM brings the same idea to the console: a decision model reads a state and answers typed questions in one forward pass, with no text generated. curl http:// < console > :8081/v1/systemone -H ' Content-Type: application/json ' -d ' { "state": "I was charged twice this month. Refund me or I cancel.", "questions": { "intent": {"type": "choice", "instructions": "What does the customer want?", "criteria": {"refund": null, "information": null, "cancel": null}}, "angry": {"type": "noul", "instructions": "Is the customer angry?"} } } ' The Suggested list has d1 Omni 600M, d1 3B and Clef Flash. Any GGUF that carries llama.cpp's decision metadata loads the same way, and the app labels it a decision model. Try it You need a PS5 on firmware 7.00 to 13.60, jailbroken, with these payloads loaded: Payload For kstuff-lite the kernel patches homebrew runs on required etaHEN homebrew support required ShadowMountPlus puts PS5LM on the home screen from /data/homebrew required elfldr (port 9021) temperature, power and real free space, through ps5-exporter recommended ftpsrv (port 2121) installing the app, copying models from a PC recommended Download ps5lm-app-vX.Y.Z.zip from the latest release and unzip it. Copy the PPSA99575 folder to /data/homebrew over FTP. ShadowMountPlus adds PS5LM to the home screen. Open PS5LM, go to Models > Suggested and get a model. Or copy a .gguf to /data/PS5LM/models , or to PS5LM/models on a USB drive. Load it. Once Home says Ready, open http://<console>:8081 in a browser, or point your OpenAI or Anthropic client at it. To update, copy the new folder over the old one. Settings, models and downloads stay in /data/PS5LM . Using it from coding tools (opencode, Codex, Claude Code) is in docs/CLI.md . Where Button Does Everywhere L1 / R1 Home, Models, API, Console, Settings Home Cross change the model Home Square / Triangle send a demo request / type a message Models D-pad, Cross choose a section and a model; load, unload or download it Models, Search L2 / R2, Square change the search; check whether a file fits Models, Downloads Cross, Square pause or resume; cancel (press twice) or clear Console L2 / R2 the last two minutes / the last hour Settings D-pad, Cross choose a category and a row; flip it, or pick from its list Settings, Diagnostics Square, Triangle app or server log; errors only Want to tinker? C++ on ps5-homebrew-ui , llama.cpp with ggml-vulkan on PS5_Vulkan 's RADV, built on Linux. Building · Console notes · Porting · Research · Models that fit · Roadmap · Changelog · The original payload Thanks abhi245y , who built the native GPU app this one grew from (PS5LM Plus). llama.cpp and ggml , which do the actual work. Mihawk-99 for PS5_Vulkan and RADV on the PS5, and PS5CEMU-HAR for the driver patches in patches/mesa . BlackBearReloaded for ps5-homebrew-ui, ps5-opengl and ps5-homebrew-dev-protocol, and John Törnblom for the SDK. Marice for ps5-exporter, which the app carries. Manrope (OFL) for the type, and PocketVibe for the interface sounds. GPL-3.0-or-later, see LICENSE . llama.cpp keeps its MIT licence, Manrope its OFL. No Sony SDK files, keys, firmware or model weights are in this repository. PS5LM is not affiliated with Sony Interactive Entertainment. "PlayStation" and "PS5" are trademarks of Sony Interactive Entertainment. (358 points, 83 comments on Hacker News)
由 claude-code/sonnet 自動生成