LLM ReferenceLLM Reference

SenseNova-U1-A3B

sensenova-u1-a3b

Open SourceMultimodalChina

About

SenseNova-U1-A3B is SenseTime's open-source multimodal MoE model released April 28, 2026. ~3B activated parameters (MoE backbone). Shares the NEO-Unify architecture with SenseNova-U1-8B: no visual encoder or VAE, native unified text-and-image representation. Apache 2.0 license. HuggingFace: OpenSenseNova/SenseNova-U1-A3B-MoT. Source: https://github.com/OpenSenseNova/SenseNova-U1

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch APIAudioFine-tuning

API Versions

sensenova-u1-a3b-mot

Rankings

Specifications

Released2026-04-28
Parameters3B
Architecturemoe
LicenseApache 2.0
Trainingpretrained

Created by

Native multimodal AI from China's vision pioneer.

Hong Kong, China
Founded 2014
Website