Qwen3 Next 80B A3B

Qwen3-Next-80B-A3B-Base is the foundation model in the Qwen3-Next series, featuring revolutionary architectural innovations for ultimate training and inference efficiency. 7% activation ratio), and native Multi-Token Prediction for faster inference.

With 80B total parameters and only ~3B activated per inference step, it achieves performance comparable to Qwen3-32B while using less than 10% training cost and delivering 10x+ throughput for 32K+ contexts.

Trained on 15T tokens with training-stability-friendly designs including Zero-Centered RMSNorm and normalized MoE router parameters. Supports 256K context length, extensible to 1M tokens with YaRN scaling.