Parcae: Stable Looped Language Model Matches Quality of Transformer Twice Its Size

Jul 11, 2026

Together AI introduces Parcae, a stable looped language model that matches the quality of a Transformer twice its size, with a 770M model achieving 1.3B-level performance. The company also presents the first scaling laws for looping, showing that increasing recurrence is a compute-efficient way to improve performance.

Why it matters: This approach could enable more efficient AI models that deliver higher performance with fewer parameters, potentially reducing computational costs and energy consumption.

Full story at: Together AI Blog ↗