--- title: Llama.cpp on a jailbroken PS5: run any GGUF model... description: PS5LM is an open-source project that runs llama.cpp on a jailbroken PlayStation 5, using the console's GPU via Vulkan to serve GGUF language models over the... canonical: https://daily.dev/posts/llama-cpp-on-a-jailbroken-ps5-run-any-gguf-model-natively-on-the-console-ehegpu47t twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console | daily.dev og:description: PS5LM is an open-source project that runs llama.cpp on a jailbroken PlayStation 5, using the console's GPU via Vulkan to serve GGUF language models over the... og:url: https://daily.dev/posts/llama-cpp-on-a-jailbroken-ps5-run-any-gguf-model-natively-on-the-console-ehegpu47t og:image: https://api.daily.dev/og/posts/EhegPU47t.png og:image:alt: Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console **[Hacker News](https://daily.dev/sources/hn)** · 7 min read · 1 upvotes · 0 comments ## Summary PS5LM is an open-source project that runs llama.cpp on a jailbroken PlayStation 5, using the console's GPU via Vulkan to serve GGUF language models over the local network. It exposes OpenAI and Anthropic-compatible APIs (compatible with Claude Code and other coding tools), a TV-based chat interface, live request monitoring, hardware telemetry, and support for 'decision models' through an Ollaya-compatible API. Benchmarks show models like Qwen 3.5 9B running at 55 tokens/sec on a PS5 Slim. Setup requires a jailbroken PS5 on specific firmware with several homebrew payloads installed. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Can I run a local LLM on a jailbroken PS5? Yes, a project called PS5LM runs llama.cpp on a jailbroken PS5's GPU using the Vulkan backend, serving GGUF models to other devices over the local network. It exposes OpenAI-compatible and Anthropic-compatible APIs, works with Claude Code, and requires firmware between 7.00 and 13.60 with homebrew payloads like etaHEN and kstuff-lite installed. _daily.dev surfaces homebrew LLM projects like this for developers exploring self-hosted inference setups._ ### How fast is LLM inference on a PS5 GPU compared to a normal setup? On a PS5 Slim running llama.cpp via Vulkan, a Qwen 3.5 0.8B model (Q4_K_M) generates about 207 tokens per second, a 9B model manages 55 tokens per second, and a 27B model quantized to UD-Q2_K_XL runs at roughly 20 tokens per second with 64k context, using 11.4 GB of the console's shared GPU memory. _developers benchmarking local inference hardware can track real-world numbers like these on daily.dev._ ### What is a decision model and how is it different from a regular LLM? A decision model answers typed questions about a given state in a single forward pass without generating text, returning choices, scores, or yes/no answers with calibrated probabilities. PS5LM implements the same /v1/systemone API used by Ollaya for this purpose, supporting models like d1 Omni 600M, d1 3B, and Clef Flash, some of which can also process images. _those evaluating lightweight decision-model APIs can follow emerging tools like Ollaya on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 2 discussions and 58 comments across hackernews (as of 2026-10-17). **TL;DR:** Reaction is mostly a mix of genuine technical interest in squeezing LLM inference out of PS5 hardware and a long tangent about whether such jailbreak projects can survive on GitHub given potential Sony takedowns, plus debate over whether a PS5 is actually a good value platform for this versus mini PCs or BC-250 mining boards. **Sentiment:** 35% positive · 40% mixed · 25% skeptical **The case for** - The PS5's GPU is seen as dramatically faster than budget mini PCs, making it a surprisingly capable local inference box despite limited VRAM. - Some think even a small quantized model running continuously is genuinely useful for low-stakes always-on tasks like monitoring or simple automation. - People find it a fun, nostalgic throwback to using idle console hardware as a cluster/compute resource. **The pushback** - Several argue the limited VRAM makes it mostly a neat stunt rather than something practically usable for serious workloads. - Others argue similarly priced or cheaper hardware (mini PCs, BC-250 boards, used GPUs) would outperform or better suit the same budget. - Concern that hosting the project primarily on GitHub leaves it vulnerable to a Sony takedown, with disagreement over how to mitigate that. **By community** - hackernews (mixed): Discussion splits between excitement about running LLMs on repurposed console hardware and skepticism about practicality and takedown risk, with a long detour into decentralized hosting alternatives. **Hottest debate:** Whether the PS5's GPU performance justifies its price compared to mini PCs or ex-mining BC-250 boards for running local LLMs. **Open questions** - Would Sony actually pursue a DMCA takedown against this kind of project, or is that concern overblown? - Is there a meaningful hardware subsidy baked into the PS5's price that this kind of repurposing undermines? **Highlights** > Even though it only runs qwen 3.8 27b at a 2 bit quant, it's still highly viable, especially for things where you just need a constant token stream of slightly below average intelligence, ie this would be great for things like: - monitoring server error rates - reviewing security footage - watching plant growth / controlling watering etc. Any long running task you can now just slap a PS5 on it. 70 cents a day in power cost means you now get ~2M output tokens per day (~$3.50 worth of usage). It's not the worst thing in the world if you have one lying around. 2bit isn't even that terrible - it's ~80% the accuracy of 27b at full quant, which should put it at around GPT-5 levels of intelligence (which honestly is crazy in its own right). > — [jjcm on hackernews](https://news.ycombinator.com/item?id=50125287) > >I'm sure someone will point out some spec that's better on the PS5 They're not even in the same ballpark - the PS5 is more than an order of magnitude better in GPU performance. Despite how much it does matter, RAM is not the only thing you need for running LLMs - that N150 is not going to run anything but really tiny models at any sort of reasonable speed - certainly nothing that approaches using all of its ram. The GPU in the PS5 is ~25x faster. And if you're running games the RAM doesn't really affect performance at all once you have "enough" for a given game. You're right that you probably could build something quite a bit faster than a PS5 for the same price though - if you can build/find everything but the GPU for ~250 USD and slap a 16gb 9060xt (~25tflops @32bit compared to the PS5 gpus ~10tflops @32bit) in it for another ~350 USD it should theoretically do a better job - the GPU in the PS5 was on par with mid-high end PC GPUs on launch, but that was like 5 years ago. > — [p1necone on hackernews · 1 comments](https://news.ycombinator.com/item?id=50125649) > Kinda cool but also entirely useless given the limited VRAM. The readme oversells it by pretending it would be something actually usable, when instead it is a cool achievement to make it happen. > — [hypfer on hackernews · 1 comments](https://news.ycombinator.com/item?id=50125016) > There's no feasible way to avoid takedowns/DMCA in 2026 unless you do TOR shenanigans. Even with a custom domain, Sony could just DMCA the web host for the project. > — [minimaxir on hackernews · 6 comments](https://news.ycombinator.com/item?id=50124081) > The project's primary site should not be GitHub, and I am serious. Playstation 5 is not some historical curiosity and Sony might strike the page down any hour now. Those projects should default to hosts less geared toward corporate governancy; custom internet domain being the first requirement. > — [Rabbit504030201 on hackernews · 4 comments](https://news.ycombinator.com/item?id=50123827) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=50122431) · 204 points · 58 comments - [hackernews](https://news.ycombinator.com/item?id=50082632) · 2 points · 0 comments ## Similar posts on daily.dev - [Running LLMs on Raspberry Pi and Edge Devices](https://daily.dev/posts/running-llms-on-raspberry-pi-and-edge-devices-vywckugzb) · SitePoint · 1 upvotes · 0 comments - [Qwen3.5 - How to Run Locally Guide](https://daily.dev/posts/qwen3-5---how-to-run-locally-guide-t89pkcicv) · Hacker News · 2 upvotes · 0 comments - [I tested 7 local LLMs on my NAS for smart home automation, and only one didn't fall apart](https://daily.dev/posts/i-tested-7-local-llms-on-my-nas-for-smart-home-automation-and-only-one-didn-t-fall-apart-nkkehvdti) · XDA Developers · 0 upvotes · 0 comments - [How to Run LLMs Locally: A Practical Guide for Developers](https://daily.dev/posts/how-to-run-llms-locally-a-practical-guide-for-developers-tijurupob) · BigData Boutique blog · 2 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#c](https://daily.dev/tags/c), [#sony](https://daily.dev/tags/sony), [#llama-cpp](https://daily.dev/tags/llama-cpp) [View this post on daily.dev](https://daily.dev/posts/llama-cpp-on-a-jailbroken-ps5-run-any-gguf-model-natively-on-the-console-ehegpu47t) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console","url":"https://daily.dev/posts/llama-cpp-on-a-jailbroken-ps5-run-any-gguf-model-natively-on-the-console-ehegpu47t","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/llama-cpp-on-a-jailbroken-ps5-run-any-gguf-model-natively-on-the-console-ehegpu47t"},"datePublished":"2026-10-16T19:53:40.116Z","dateModified":"2026-10-17T02:09:45.751Z","description":"PS5LM is an open-source project that runs llama.cpp on a jailbroken PlayStation 5, using the console's GPU via Vulkan to serve GGUF language models over the...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/94f1536fb556ea14cb04111b90bf82b2?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/94f1536fb556ea14cb04111b90bf82b2?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/llama-cpp-on-a-jailbroken-ps5-run-any-gguf-model-natively-on-the-console-ehegpu47t","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,c,sony,llama-cpp","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/llama-cpp-on-a-jailbroken-ps5-run-any-gguf-model-natively-on-the-console-ehegpu47t#faq","mainEntity":[{"@type":"Question","name":"Can I run a local LLM on a jailbroken PS5?","acceptedAnswer":{"@type":"Answer","text":"Yes, a project called PS5LM runs llama.cpp on a jailbroken PS5's GPU using the Vulkan backend, serving GGUF models to other devices over the local network. It exposes OpenAI-compatible and Anthropic-compatible APIs, works with Claude Code, and requires firmware between 7.00 and 13.60 with homebrew payloads like etaHEN and kstuff-lite installed. daily.dev surfaces homebrew LLM projects like this for developers exploring self-hosted inference setups."}},{"@type":"Question","name":"How fast is LLM inference on a PS5 GPU compared to a normal setup?","acceptedAnswer":{"@type":"Answer","text":"On a PS5 Slim running llama.cpp via Vulkan, a Qwen 3.5 0.8B model (Q4_K_M) generates about 207 tokens per second, a 9B model manages 55 tokens per second, and a 27B model quantized to UD-Q2_K_XL runs at roughly 20 tokens per second with 64k context, using 11.4 GB of the console's shared GPU memory. developers benchmarking local inference hardware can track real-world numbers like these on daily.dev."}},{"@type":"Question","name":"What is a decision model and how is it different from a regular LLM?","acceptedAnswer":{"@type":"Answer","text":"A decision model answers typed questions about a given state in a single forward pass without generating text, returning choices, scores, or yes/no answers with calibrated probabilities. PS5LM implements the same /v1/systemone API used by Ollaya for this purpose, supporting models like d1 Omni 600M, d1 3B, and Clef Flash, some of which can also process images. those evaluating lightweight decision-model APIs can follow emerging tools like Ollaya on daily.dev."}}]} ```