Overview
An experimental model built on V3.1-Terminus, introducing DeepSeek Sparse Attention for long-context efficiency.
DeepSeek-V3.2-Exp
An experimental model built on V3.1-Terminus, introducing DeepSeek Sparse Attention for long-context efficiency.
MODEL NUMBER229
- First public date
- 2025-09-29
- Organization
- DeepSeek
- Family
- DeepSeek V / R
01
Specifications
Only published specifications are shown.
02
Overview
03
Architecture & capabilities
Attention
DeepSeek Sparse Attention
04
Release history
DeepSeek-V3.2-Exp released model weights.
View source05
Related models
Select a card to view the related model.
06