Instructions to use Qwen/Qwen3-Omni-30B-A3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3-Omni-30B-A3B-Instruct with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Instruct") model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Instruct") - Notebooks
- Google Colab
- Kaggle
Plans for omni 3.5 or 3.6
#34
by RSTAS - opened
Hey, is there plans for releasing omni 3.5 or 3.6 open weights? This feels bit outdated compared to newer qwen releases
Yes please! The open space is sorely leaking omni model and the qwen3 full attention architecture is quite old at this point and consumes a lot of KV cache. A 3.5 update would be greatly appreciated by the whole community!
A 3.5 update would be greatly appreciated by the whole community!