Qwen3-Omni#
Qwen3-Omni is Alibaba Cloud’s omnimodal model supporting text, image, audio, and video inputs in a single unified architecture with a MoE language backbone.
Task |
Omnimodal (Text·Image·Audio·Video) |
Architecture |
|
Parameters |
30B total / 3B active |
HF Org |
Available Models#
Qwen3-Omni-30B-A3B: 30B total, 3B activated (MoE)
Architecture#
Qwen3OmniForConditionalGeneration
Example HF Models#
Model |
HF ID |
|---|---|
Qwen3-Omni 30B A3B |
Example Recipes#
Recipe |
Dataset |
Description |
|---|---|---|
MedPix-VQA |
SFT — Qwen3-Omni 30B with TE + DeepEP |
Try with NeMo AutoModel#
1. Install (full instructions):
pip install nemo-automodel
2. Clone the repo to get the example recipes:
git clone https://github.com/NVIDIA-NeMo/Automodel.git
cd Automodel
3. Run the recipe from inside the repo:
automodel --nproc-per-node=8 examples/vlm_finetune/qwen3/qwen3_omni_moe_30b_te_deepep.yaml
Run with Docker
1. Pull the container and mount a checkpoint directory:
docker run --gpus all -it --rm \
--shm-size=8g \
-v $(pwd)/checkpoints:/opt/Automodel/checkpoints \
nvcr.io/nvidia/nemo-automodel:26.02.00
2. Navigate to the AutoModel directory (where the recipes are):
cd /opt/Automodel
3. Run the recipe:
automodel --nproc-per-node=8 examples/vlm_finetune/qwen3/qwen3_omni_moe_30b_te_deepep.yaml
See the Installation Guide and Omni Fine-Tuning Guide.
Fine-Tuning#
See the VLM / Omni Fine-Tuning Guide.