I ran a language model on a PS2
The Emotion Engine has 32 MB of RAM total, so the trick is streaming weights from CD-ROM one matrix at a time during the forward pass — only activations, KV cache and embeddings live in RAM. This means models bigger than the RAM can still run, they just read more from disc. Had to build a custom quantized format (PSNT), hack endianness, write a tokenizer pipeline, and most of the PS2 SDK from scratch (releasing that separately). The model itself is also custom — a 10M param Llama-style architecture I trained specifically for this. And it works. On real hardware.
In plain words
A language model implementation that runs on PlayStation 2 hardware despite the console's 32 MB RAM limitation. The project streams model weights from CD-ROM during inference, keeping only activations and embeddings in memory. It includes a custom quantized format, a 10-million parameter Llama-style model trained for the platform, and a rebuilt PS2 SDK. The implementation functions on actual PS2 hardware, enabling AI inference on legacy gaming consoles.
written from the facts on this page · September 2026
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
