Saturday, March 21, 2026

Show HN: Can I run a model language on a 26-year-old console? https://ift.tt/wdfu2Gz

Show HN: Can I run a model language on a 26-year-old console? Short answer: yes. 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. https://ift.tt/hoJAOZe March 22, 2026 at 12:57AM

No comments:

Post a Comment

Show HN: Fork – Let users build features on top of existing applications https://ift.tt/8NMkxKH

Show HN: Fork – Let users build features on top of existing applications Our initial release is a Chrome extension that builds on top of Gma...