TurboQuant: How a Simple Spin Saves Gigabytes of GPU Memory
Start With a Restaurant Before we talk about AI, let me tell you about a busy...
Apr 8, 20266 min read0 reactions0 comments
Back to articles Apr 8, 2026 
Apr 7, 2026
Mar 31, 2026
Tag archive
#turboquant
Google Dropped TurboQuant Two Weeks Ago. The Community Already Made It Usable.
Two weeks after Google published their TurboQuant paper at ICLR 2026, five independent implementations exist -- including one running a 104B model on a MacBook. What the community built, what works today, and what it means.
Apr 7, 20266 min read1 reactions0 comments
T
Mar 25, 2026TurboQuant: Redefining AI efficiency with extreme compression!
The pervasive adoption of large language models (LLMs) and other deep neural networks has ushered in...
Mar 25, 202612 min read0 reactions0 comments
B
Mar 30, 2026Building a Vector Database That Never Decompresses Your Vectors
Preamble: What vector search is all about If you've spent any time near an LLM in the...
Mar 30, 202616 min read2 reactions0 comments
TurboQuant and RaBitQ: What the Public Story Gets Wrong
Hi everyone. My name is Jianyang Gao. I am currently a postdoctoral researcher at ETH Zurich, and I...
Mar 31, 20267 min read6 reactions4 comments