Adapt
Mini toolsChinchilla
Chinchilla is a 70B-parameter DeepMind language model trained on 1.3T tokens. It is best known for the Chinchilla scaling-law result, showing that for a fixed compute budget, smaller models trained on more data can outperform larger undertrained models, including Gopher, despite having far fewer parameters.
Text
Gen 2
Overview
Chinchilla is DeepMind’s 70B language model used to demonstrate compute-optimal scaling with more training data and fewer parameters than larger undertrained models.
About Google DeepMind
AI research lab within Google developing frontier models, scientific AI systems, reinforcement learning methods, and products that support Google services and research.
Industry:
Artificial Intelligence
Company Size:
6000
Location:
London, England, GB
Website:
deepmind.com
Tools using Chinchilla
No tools found for this model yet.
Last updated: June 2, 2026
