SenseNova Loop-9B-Preview model open-sourced by Megvii
The story so far
SenseTime open-sources SenseNova Loop-9B-Preview model, claims to match 27B model size with only 9B parameters, and outperforms other models, including Qwen3.5-27B, in code generation, office scenarios, and intelligent agent tasks. The model uses a Looped Transformer architecture, retaining 4 layers of original decoder modules at the beginning and end, and transforming the middle layers into parameter-sharing cyclic computation modules to expand effective computational depth through multi-round iterations. SenseTime announced this open-source initiative on October 30.
AI-written from the reports · Updated 18 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- ITHome · AISenseNova Loop-9B-Preview open sourced by Megvii, claims to match the performance of 27B parameter models
Megvii open sourced the SenseNova Loop-9B-Preview model, which uses the Looped Transformer architecture and matches the performance of 27B models with just 9B parameters, outperforming other models including surpassing Qwen3.5-27B in code generation, office scenarios, and intelligent agent tasks