Qwen3-Next-80B-A3B
by Alibaba
· Qwen3-Next family · released Sep 22, 2025
Open weights
Active
Alibaba's next-generation architecture combining gated deltanet linear attention with gated attention in a MoE (80B total / 3B active), with 256K native context expandable to 1M tokens.
No pricing recorded for this model yet.
Specifications
| Model type | Text LLM |
|---|---|
| Architecture | Hybrid |
| Parameters | 80 (3 active) |
| Context window | 262.1K tokens |
| Max output | Not disclosed tokens |
| Knowledge cutoff | Not disclosed |
| License | Apache License 2.0 |
| Modalities | Text input Text output |
| Tags | Long context |
| End of life | Not disclosed |
| Weights | Download |
| Last verified | Not disclosed |