← Library · Frontier
Thinking Machines Lab Releases Inkling-Small, a Mixture-of-Experts Transformer
Thinking Machines Lab has introduced Inkling-Small, a Mixture-of-Experts (MoE) transformer model. This model features a total of 276 billion parameters, with 12 billion parameters active at any given time. MoE models are designed to be more efficient, activating only a subset of their parameters for specific tasks, which can lead to faster inference and training.
Why it matters
The release of Inkling-Small contributes to the growing trend of open-source Mixture-of-Experts models, offering a potentially more efficient architecture for various AI applications, especially for developers and researchers.
Learn one new AI thing every day.
Daily Deck sends you seven plain-English cards like this every morning. Free.
Start free