Sheikyon/LLM-X

Python library for precise, hardware-aware inference memory consumption estimation of language models via reverse-engineering the model's tensors.

1 best points · 0 comments · 1 Hacker News post · 4 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: LLM-X – Know How Much Memory Your LLM Needs (1 points, 0 comments, by sheikyon, 2026-01-22)