ZMIME

WeMM-Video-35B-A3B vs Aion 1.0 Instruct 2.3B

Compare documented capabilities and access. A dash means a comparable figure is unavailable.

Model specifications
SpecificationWeMM-Video-35B-A3BTencentAion 1.0 Instruct 2.3BMicrosoft
TaskAudio-visual understandingOn-device language generation
Published capabilitiesAnswers questions in Chinese or English about video frames and their soundtrack. Supports direct responses and a thinking mode.Windows-oriented instruction model for local text generation, including document and email tasks.
Model size35B total / 3B active MoE backbone2.3B parameters
AccessPublic BF16 checkpoint and quantized releasesDownloadable checkpoint
ResultText responses, including descriptions and speech transcripts—
Operating limits—32K-token context window
SourcesModel weights · Additional documentationModel weights
InputsText, Images, Audio, VideoText
WeightsOpen weights · Apache-2.0Open weights · MIT
ReleasedNov 20, 2026Nov 18, 2026