← Latest products

TurboQuant

New LLM compression algorithm by Google. A set of advanced theoretically grounded quantization algorithms that enable massive compression for large language models and vector search engines.

Visit research.googleexternal site

Reactions (1)

Similar products

by description similarity

  1. TurboQuant-WASM

    github.com

    Google's vector quantization in the browser

    Hacker News165 pts

  2. TurboQuant for vector search

    github.com

    2-4 bit compression

    Hacker News89 pts

  3. I made a new compression algorithm

    github.com

    Improving classic Lempel-Ziv-Welch with edit distance matching

    Hacker News9 pts

  4. UltraCompress

    github.com

    first mathematically lossless 5-bit LLM compression

    Hacker News6 pts

  5. KTransformers:671B DeepSeek-R1 on a Single Machine-286 tokens/s Prefill

    github.com

    A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

    Hacker News20 pts