Skip to content
Model library

Qwen

Qwen3.8-Flash-Next

A sparse multimodal model for coding, visual understanding, and multi-step agent tasks.

Language models
Checkpoint
About 180B parameters
Input
Text / images / video
Output
Text
Native context
262K tokens

Build with it

  • Coding and research agents
  • Visual document analysis
  • Long-context assistants
Original model card & license