Diggnation (Rebooted) cover image

Sora 2 Breaks Reality, Neurotech Zaps Your Brain, Instagram Still Confused | E21 | Diggnation

Diggnation (Rebooted)

00:00

Huawei Shrinks LLMs for Local Use

Kevin explains Huawei's quantization work (SYNQ) to reduce LLM memory, enabling offline models on consumer GPUs and local privacy benefits.

Play episode from 26:13
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app