Qwen3-Omni-30B-A3B-Thinking

CheckpointQwen/Qwen3-Omni-30B-A3B-ThinkingModel card indexedModel card

Support summary

Qwen3-Omni-30B-A3B-Thinking is a checkpoint published by Qwen, built on the Qwen3OmniMoeThinkerForConditionalGeneration and Qwen3OmniMoeForConditionalGeneration architectures. vLLM 0.28.0, the newest indexed vLLM release, documents support.

vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.

License: apache-2.0

Hugging Face model card

Publisher: Qwen
Task: any to any
License: apache-2.0
Library: transformers
Architecture: Qwen3OmniMoeForConditionalGeneration
Weight tensor elements: 31.7B
Tensor types: BF16
Languages: en
Weight access: Public
Repository created: 2025-09-15

Source 1 Source 2 Source 3Reviewed 2026-09-05

Model notes and sources

vLLM v0.28.0 · docs/models/supported_models.md · 20 indexed revisions, v0.17.0 to v0.28.0
Qwen/Qwen3-Omni-30B-A3B-Thinking · publisher model card
Qwen/Qwen3-Omni-30B-A3B-Thinking · Hugging Face metadata
Qwen/Qwen3-Omni-30B-A3B-Thinking · publisher configuration
Reviewed 2026-09-05

Engine support

3 engines

Engine support for Qwen3-Omni-30B-A3B-Thinking
Engine	Release	Evidence scope	Last known supported
vLLM	`0.28.0`Newest indexed	Checkpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed 2026-09-05	`0.28.0`This release
Features, dependencies and evidence for vLLM 0.28.0
SGLang	`0.5.19`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM	`1.2.1`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1