tac0mania/taco

GPT-2 with zero floats: compress on a Mac, decompress on Windows/CUDA/Vulkan, byte-for-byte identical. Lossless LLM compression that doesn't break when the hardware changes. (alpha)

2 best points · 2 comments · 2 Hacker News posts · 11 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: I removed every float from GPT-2 for identical neural compression (2 points, 2 comments, by taco-man, 2026-10-20)
• Show HN: Taco - LLM compression that gives the same bytes on every CPU and GPU (1 points, 0 comments, by taco-man, 2026-10-19)