HuggingFace

Model instances

Ling-1T

With 1 trillion total parameters and ≈ 50 billion active per token, Ling-1T uses a MoE design optimized through the Ling Scaling Law for trillion-scale stability. The model was trained on more than 20 trillion high-quality, reasoning-dense tokens, supporting up to 128K context length.

Why should you use Ling-1T:

Reading

Articles


Tags: ai   model   llm  

Last modified 22 March 2026