QW

Qwen3-Omni-30B-A3B

Multimodal modelQwen3

Qwen3-Omni-30B-A3B-Instruct

Release date: 2025-09-22Updated: 2025-09-23 08:35:27915
Parameters
30B
Context length
128K
Chinese support
Supported
Reasoning ability

Qwen3-Omni-30B-A3B-Instruct is an AI model published by 阿里巴巴, released on 2025-09-22, for Multimodal model, with 30B parameters, and 128K context length, requiring about 60GB storage, under the Apache 2.0 license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Qwen3-Omni-30B-A3B

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
No data
Model type
Multimodal model
Modality (in / out)
Text, Image, Audio, Video → Text, Image, Audio, Video
Release date
2025-09-22
Model file size
60GB
MoE architecture
Yes
Total params / Active params
30B / 3B
Knowledge cutoff
No data
Qwen3-Omni-30B-A3B

Open source & experience

Qwen3-Omni-30B-A3B

Official resources

Paper
No paper available
DataLearnerAI blog
No blog post yet
Qwen3-Omni-30B-A3B

API details

API speed
3/5
No public API pricing yet.
Qwen3-Omni-30B-A3B

Benchmark Results

No benchmark data to show.

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Qwen3-Omni-30B-A3B

Publisher

Qwen3-Omni-30B-A3B-Instruct

Model Overview

Qwen3-Omni-30B-A3B-Instruct is an AI model published by 阿里巴巴, released on 2025-09-22, for Multimodal model, with 30B parameters, and 128K context length, requiring about 60GB storage, under the Apache 2.0 license.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code