Instructions to use Qwen/Qwen3-Omni-30B-A3B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3-Omni-30B-A3B-Thinking with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Thinking") model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Thinking") - Notebooks
- Google Colab
- Kaggle
quantizes
#6
by LeroyDyer - opened
will there be quantizes please?
Also moe is always great especially as you have trained the full 8 experts ! (very good , but locally it take ages to respond _ )
could you make a 30 non moe model ? as it seems with good RAM these models can be loaded locally with partial gpu and cpu settings ! so even with a low gpu it can be loaded locally ! ( quantized ) (Q4)