Qwen2.5-72B-Instruct

Qwen2.5-72B-Instruct is a flagship 72.7-billion parameter, open-weight model engineered for high-stakes AI production, advanced reasoning, and complex conversational tasks. Optimised with an 80-layer architecture using Grouped Query Attention (GQA), it delivers exceptional performance in coding, mathematics, and structured data tasks like JSON and table processing.