Qwen3-Omni-30B-A3B-Thinking is part of the Qwen3 family, combining a 30B-parameter model with a smaller 3B active component for efficient multimodal (text + vision) processing and advanced reasoning. It includes native tool-calling support and specialized thinking templates. The model is released as open weights on Hugging Face for local or cloud inference.
In the Foundation models & chat space, Qwen3 Omni 30B A3B Thinking takes a focused approach. It focuses on building applications that require multimodal understanding, reasoning, and tool use in a single open model. Qwen3 Omni 30B A3B Thinking is an open-source project aimed at developers. The project is open source (Apache-2.0). The product ships for the web, the command line, and API.
Qwen builds and maintains Qwen3 Omni 30B A3B Thinking, and the product first shipped in 2025. The project is developed in the open on GitHub with 3.9k stars and 3 commits in the last 90 days. Among its 3 catalogued features are multimodal input, tool calling, and thinking mode.
Latest indexed changes and source events
Qwen/Qwen3-Omni-30B-A3B-Thinking verified by the PulseGate indexer
