xaskasdf/ps2-llm

A custom LLM runtime for the Sony PSP, running a 90M parameter language model locally.

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

A simple LLM-based chat app that runs on the PS5 GPU

TinyStories-260K running locally on a stock Game Boy Color.

Run a 1-billion parameter LLM on a $10 board with 256MB RAM

Inference engine for large language models on consumer GPUs, with deep optimization for older hardware

Running a LLM on the ESP32

Local LLM inference on Xbox Series S|X in Dev Mode: llama.cpp (GGUF) + ONNX Runtime GenAI, opt-in OpenAI-compatible LAN endpoint, diffusion and on-device training. Measured models are listed in a Hugging Face collection. Independent research project, not affiliated with Microsoft.