Jailbroken PS4 runs 9-billion-parameter AI model at up to 43 tokens per second
- ID
- 47019
- Status
- summarized
- Published
- 16 Nov 2026, 9:00 PM
- Fetched
- 16 Nov 2026, 10:33 PM
- Provider
- Tom's Hardware
- Category
- technology
- Original URL
- https://www.tomshardware.com/video-games/playstation/jailbroken-ps4-runs-9-billion-parameter-ai-model-at-up-to-43-tokens-per-second-open-source-garlic-llm-bypasses-drivers-to-talk-directly-to-the-2013-era-gpu
- Source URL
- https://www.tomshardware.com/feeds/all
Summary
- Score
- 5.5
- Created
- 16 Nov 2026, 10:34 PM
- Tags
- Audience
- developersai_ml_learners
What happened
Tom's Hardware reports that a jailbroken PS4 can run a 9-billion-parameter AI model at up to 43 tokens per second using an open-source project called Garlic LLM, which bypasses standard drivers to communicate directly with the console's 2013-era GPU. The supplied page text is almost entirely site navigation and subscription boilerplate, so the model used, quantization, memory footprint, and setup steps are not stated. Treat this as a headline-level report only.
Why it matters
The one usable signal is the ratio: 43 tok/s for a 9B model on a decade-old console GPU implies the software stack — drivers and kernels — is often the binding constraint, not raw silicon. That is relevant if you are sizing cheap or used hardware for local inference instead of buying new GPUs. But with no memory footprint, quantization, or context-length numbers in the text, you cannot yet judge whether the result is reproducible or comparable to a normal llama.cpp setup, so do not plan a build around it.
Discussion angle
If skipping the driver layer buys this much throughput on 2013 console hardware, what is the equivalent shortcut for the hardware builders here actually own — used mining GPUs, laptops, ARM boxes — and where does that approach fall over: memory bandwidth, thermals, or model quality?