jhammant/Turbo1bit

Turbo1Bit: Combining 1-bit LLM weights (Bonsai) with TurboQuant KV cache compression for maximum inference efficiency. 4.2x KV cache compression + 16x weight compression = ~10x total memory reduction.

1 best points · 0 comments · 1 Hacker News post · 30 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Turbo1Bit – Run Bonsai-8B at 65K context in 3.9 GB RAM (1 points, 0 comments, by tetsuto, 2026-04-02)