I ran a language model on a PS2
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
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.
HN · launched Mar 21, 2026 · 46 upvotes (top 17%) · 0 views
Niche: llm inference engines · 133 launches, 4 in the last 7 days ▼ -33% · Explore this niche →
Category and tags
- Horizontal
- Model & infra
- Developer
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 133 launches in llm inference engines →
Could you build this?
No Porting an LLM forward pass to bare-metal PlayStation 2 hardware (Emotion Engine) with 32 MB of RAM and optical disc streaming requires deep embedded systems, assembly/MIPS architecture, and custom quantization expertise.
What it would actually take: Requires low-level C/MIPS assembly and PS2 homebrew SDKs (PS2DEV). The engineering involves designing a custom quantization pipeline, paging matrix weights synchronously or via DMA from the CD-ROM drive into tight scratchpad/main RAM, and handling hardware vector units (VU0/VU1) for inference math without standard OS abstractions.
Discussion
12 comments analyzed.
Competitors mentioned: Open PS2 Loader, PS2Linux, RenderWare
Concerns raised: PS2 processors can't push full 100Mbit ethernet speed, USB 1.1 much slower than CD interface, 32MB RAM constraint limits model size, Development still hard for newcomers, CD-ROM streaming latency with larger models
Feature requests: Support for larger models via HDD/Memory Card adapters, Leverage EE vector units for inference performance, Multiplayer support for Age of Empires II, Open source RenderWare
Competitors
Other products that read as similar to this one : 328 launches clear the similarity bar, closest 8 shown.
Attention rank: #75 of 329 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 143 days after the earliest competitor.
- Z80-μLM, a 'Conversational AI' That Fits in 40KB · hn · 2025-12-29 · 514 upvotes · similarity 0.48
- Moonshine Open-Weights STT models · hn · 2026-02-24 · 316 upvotes · similarity 0.45
- You can now train your own LLMs with less memory, on your consumer GPUs · hn · 2026-11-10 · 5 upvotes · similarity 0.45
- L88 · hn · 2026-02-24 · 12 upvotes · similarity 0.44
- Serve 100 Large AI models on a single GPU with low impact to TTFT · hn · 2025-11-08 · 7 upvotes · similarity 0.44
- Supermodel-VK · github · 2026-10-17 · 29 upvotes · similarity 0.43
- A decent text-to-image model trained for ~$20K (Apache 2.0 Weights) · hn · 2026-11-04 · 284 upvotes · similarity 0.42
- SPECTRA · ph · 2026-11-11 · 1 upvotes · similarity 0.42
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.