PacifAIst/Quansloth

Based on the implementation of Google's TurboQuant (ICLR 2026) — Quansloth brings elite KV cache compression to local LLM inference. Quansloth is a fully private, air-gapped AI server that runs massive context models natively on consumer hardware with ease

2 best points · 1 comments · 1 Hacker News post · 153 GitHub stars · View on GitHub

Hacker News discussions

• Quansloth Using Google's Turboquant Breaks the "VRAM Wall" for Local LLMs (2 points, 1 comments, by gunzfanatic, 2026-04-07)