opengraviton/graviton-native

Efficient LLM architectures for 32GB RAM — BitNet & MoE

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

Hacker News discussions

• Show HN: Efficient LLM Architectures for 32GB RAM (Ternary and Sparse Inference) (2 points, 1 comments, by fatihturker, 2026-03-09)