Jailbroken PS5s can now run local AI models at over 100+ tokens per second

PS5LM gets a fork, allowing it to run natively and use the GPU and more RAM to run larger LLMs, even running Qwen3.8-27B at 20 tokens per second.

Read the full story at Tom's Hardware ↗

Timeline · 1 report

2026-10-16 10:00 · Tom's Hardware
Jailbroken PS5s can now run local AI models at over 100+ tokens per second

More stories

NVIDIA RTX Spark Laptops Launch Globally With AI Agent Support — NVIDIA Blog
Meta releases open weights for 816B-parameter Muse Spark AI model — AWS Machine Learning Blog
"Mommy and daddy" play nice: Apple and Meta team up to bring open-source Muse to Macs — Axios AI+
Taiwan to Curb AI Chip Exports to China Under US Trade Deal — Bloomberg AI
AGI may already be here, we’re just too dependent to notice — Fast Company AI
New Elizabeth Holmes documentary sparks discussion on tech industry impact — Hard Fork (NYT)
Microsoft Surface Laptop Ultra features Nvidia RTX Spark for local AI — Tom's Hardware
AI faces insurance hurdles as safety incidents raise liability risks — Wall Street Journal Technology

Get the daily brief of stories like this at 6:30 every morning →