Project AURIONAI Use-Cases Research & Innovation
Alibaba (Qwen)
multimodal LLM

Qwen3-Omni-30B-A3B-Instruct

Natively omni-modal Qwen3 model that takes text, images, audio and video and answers in text and real-time speech.

Alibaba (Qwen)Alibaba (Qwen)China
Diagram of the Qwen3-Omni thinker and talker architecture for text, image, audio and video.
Levelmodel
Classmultimodal LLM
Parameters35.26B
Contextnot in the notes
Released20 Sep 2025
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

R&D Topics

Omni-modal and unified multimodal modelsproduced by

Identity

Developer
Alibaba (Qwen)
Family
not in the notes
Released
20 Sep 2025 sourcesregistry date
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
MoE
Total parameters
35.26B sources
Active parameters
–
Checkpoint parameters
–
Note
Parameter count from the safetensors index on Hugging Face.
Context length
not in the notes
Input
text, image, video, audio
Output
text, audio
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
Model card languages: en
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct
  2. huggingface.co/api/models?pipeline_tag=any-to-any&sort=downl... https://huggingface.co/api/models?pipeline_tag=any-to-any&sort=downloads&limit=50
  3. modelscope.cn/models/Qwen/Qwen3-Omni-30B-A3B-Instruct https://www.modelscope.cn/models/Qwen/Qwen3-Omni-30B-A3B-Instruct

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Qwen3-Omni-30B-A3B-Instruct", https://aurion.semai.id/models/alibaba-qwen3-omni-30b-a3b-instruct/, records of October 2026.