Jailbroken PS5s can now run local AI models at over 100+ tokens per second
- ID
- 36210
- Status
- summarized
- Published
- 16 Oct 2026, 6:00 PM
- Fetched
- 16 Oct 2026, 6:48 PM
- Provider
- Tom's Hardware
- Category
- technology
- Original URL
- https://www.tomshardware.com/video-games/playstation/jailbroken-ps5s-can-now-run-local-ai-models-at-over-100-tokens-per-second-fork-of-ps5lm-goes-native-and-accesses-gpu-and-more-ram
- Source URL
- https://www.tomshardware.com/feeds/all
Summary
- Score
- 4.5
- Created
- 16 Oct 2026, 6:49 PM
- Tags
- Audience
- developersai_ml_learners
What happened
A fork of PS5LM reportedly now runs natively on jailbroken PlayStation 5 consoles, with Tom's Hardware's headline claiming over 100 tokens per second by taking over the CPU and accessing the GPU and more RAM. The available excerpt is almost entirely page navigation, subscription prompts, and newsletter signup copy, so it contains no details on which models were run, at what quantization, with what context length, or what the actual RAM ceiling was.
Why it matters
The '100+ tokens per second' number is only useful with the model size attached — a tiny quantized model at that speed is a very different claim from a 7B or 13B model, and the text doesn't say which, so this can't be used to compare against a Mac, an RTX card, or a cloud endpoint. Treat it as a curiosity, not a purchasing or architecture signal: the only concrete facts here are 'jailbroken PS5', 'native fork of PS5LM', and '100+ tokens/sec', none of which tell you whether this is reproducible or supported for anything you'd ship.
Discussion angle
If the model, quantization, and memory numbers were published, would this change how anyone thinks about local inference hardware — or is the interesting part just that console GPUs are now reachable by open-source runtimes at all?