Qwen3-Next-80B-A3B-Instruct
by Alibaba
· Qwen3-Next family · released Sep 23, 2025
Open weights
Active
Open-weights 80B-total/3B-active MoE combining gated Deltanet linear attention with gated attention for ~10x decode throughput and ultra-long-context performance; released ahead of the Yunqi Conference.
No pricing recorded for this model yet.
Specifications
| Model type | Text LLM |
|---|---|
| Architecture | Hybrid |
| Parameters | 80 (3 active) |
| Context window | Not disclosed tokens |
| Max output | Not disclosed tokens |
| Knowledge cutoff | Not disclosed |
| License | Apache License 2.0 |
| Modalities | Text input Text output |
| Tags | Agentic Coding Long context |
| End of life | Not disclosed |
| Weights | Download |
| Last verified | Not disclosed |