# SenseTime previews a 9B looped-transformer VLM

> SenseNova-Loop-9B-Preview puts a recurrent-depth architecture to work on multimodal reasoning.

Published by The Open Weights on Oct 28, 2026. Canonical: https://theopenweights.com/news/sensenova-loop-9b-3560

## Key facts

- Company: SenseTime
- Model: SenseNova-Loop-9B-Preview
- Version: Loop-9B Preview
- Category: Vision-Language
- Modalities: Reasoning, Vision-Language
- License: Other (Open weights, commercial use allowed)
- Parameters: 9B
- Context window: 262K tokens
- Architecture: SenseNovaLoopForConditionalGeneration
- Precision: FP32
- Weights size: 38.1 GB
- Significance: notable
- Published: 2026-10-28
- Last verified: 2026-11-05
- Hugging Face: https://huggingface.co/sensenova/SenseNova-Loop-9B-Preview
- Canonical URL: https://theopenweights.com/news/sensenova-loop-9b-3560

SenseTime has released an early look at SenseNova-Loop-9B-Preview, a 9-billion-parameter vision-language model that leans on a "looped" transformer design. The model is available now on [Hugging Face](https://huggingface.co/sensenova/SenseNova-Loop-9B-Preview), carrying a preview label that signals the work is still maturing.

The headline idea is architectural. Rather than simply stacking more layers, a looped transformer reuses a block of weights across multiple passes, trading raw parameter count for repeated computation at inference time. That approach can let a comparatively small model spend more effort on hard problems, which fits neatly with the model's billing as a multimodal reasoning system.

## Why it matters

Most of the attention in open multimodal models has gone to scaling parameters and context windows. A recurrent-depth design points at a different lever:

- A dense 9B footprint that stays practical to run
- Extra reasoning capacity drawn from looping rather than size
- A focus on vision-language tasks that reward deliberate, multi-step inference

As a preview, the release is best read as a statement of direction from SenseTime rather than a finished product. Key details such as context length and formal benchmarks aren't spelled out in the record, and the model ships under a custom license, so teams will want to check the terms before building on it. Still, it is a concrete entry in the growing experiment around making smaller models think harder.

## Get the model

- [Hugging Face](https://huggingface.co/sensenova/SenseNova-Loop-9B-Preview)

## Sources

- [sensenova/SenseNova-Loop-9B-Preview](https://huggingface.co/sensenova/SenseNova-Loop-9B-Preview) — Hugging Face, Oct 28, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "SenseTime previews a 9B looped-transformer VLM", The Open Weights, Oct 28, 2026, https://theopenweights.com/news/sensenova-loop-9b-3560