# QJL residual correction needed or harmful > Hannecke's survey reports the community independently found that at 3 or more bits putting all bits into Lloyd-Max centroids beats the paper's two-stage QJL scheme, so TurboQuant in practice is random rotation plus Lloyd-Max scalar quantization, while at 2.5 bits QJL remains necessary. Parent: [Mac local LLMs: KV cache sizing and quantization](https://llms-explorer.com/tree/mac-local-llms-kv-cache-sizing-and-quantization/) · 1 facets · 1 facts · page: https://llms-explorer.com/tree/qjl-residual-correction-needed-or-harmful/ ## Facts - Hannecke's survey reports the community independently found that at 3 or more bits putting all bits into Lloyd-Max centroids beats the paper's two-stage QJL scheme, so TurboQuant in practice is random rotation plus Lloyd-Max scalar quantization, while at 2.5 bits QJL remains necessary. — [source](https://medium.com/@michael.hannecke/turboquant-on-apple-macos-five-integration-paths-for-local-kv-cache-compression-42e83959d414)