Audio Edition: How Distillation Makes AI Models Smaller and Cheaper
From The Quanta Podcast by Quanta Magazine
May 14, 2026 · 8 min
About this episode
The episode discusses how distillation allows researchers to train smaller and cheaper AI models using larger teacher models.
Fundamental technique lets researchers use a big, expensive “teacher” model to train a “student” model for less. The story How Distillation Makes AI Models Smaller and Cheaper first appeared on Quanta Magazine.
Topics covered
- AI
- distillation
- machine learning
- model training
- cost reduction
Keywords
- distillation
- AI models
- machine learning
- training
- cost efficiency
Mentioned in this episode
Organizations: Quanta Magazine
Books & works: How Distillation Makes AI Models Smaller and Cheaper
More episodes of The Quanta Podcast
- Ecotypes Make the Idea of a Species Even Fuzzier · June 9, 2026 · 27 min
- What Actually Causes Lightning? · June 2, 2026 · 22 min
- Audio Edition: Astrophysicists Find No ‘Hair’ on Black Holes · May 28, 2026 · 13 min
- The AI Revolution in Math Has Arrived · May 26, 2026 · 30 min
- Ice Is Way More Complex Than It Seems · May 19, 2026 · 25 min
- Our Immune Systems Are Full of Ancient Weapons · May 12, 2026 · 30 min
Explore listener stats, chart rankings, contacts and more on the The Quanta Podcast podcast page.