The Neural Daily

The Neural Deep Dive 2026-07-15: Cheating the Hardware Limit

13 min · I går
episode The Neural Deep Dive 2026-07-15: Cheating the Hardware Limit cover

Description

Break the link between model size and compute cost. We dive into the "Sparse Mixture-of-Experts" revolution, exploring how the Llama 4 Scout architecture uses dynamic routing and 4-bit quantization to bring trillion-parameter intelligence to local hardware. From "routing collapse" to the promise of decentralized AI, discover why smarter routing is replacing bigger models.

Comments

0

Be the first to comment

Sign up now and become a member of the The Neural Daily community!

Get Started

1 month for 9 kr.

Then 99 kr. / month · Cancel anytime.

  • Podcasts kun på Podimo
  • 20 lydbogstimer pr. måned
  • Gratis podcasts

All episodes

206 episodes