Model CoverageVision Language Models

Qwen3-VL / Qwen3-VL-MoE

View as Markdown

Qwen3-VL is Alibaba Cloud’s third-generation vision language model series. The MoE variant activates a fraction of parameters per token for efficient large-scale inference.

TaskImage-Text-to-Text
ArchitectureQwen3VLForConditionalGeneration
Parameters4B – 235B
HF OrgQwen

Available Models

  • Qwen3-VL-8B-Instruct: 8B
  • Qwen3-VL-4B-Instruct: 4B
  • Qwen3-VL-MoE-30B: 30B total (MoE)
  • Qwen3-VL-MoE-235B: 235B total (MoE)

Architecture

  • Qwen3VLForConditionalGeneration

Example HF Models

ModelHF ID
Qwen3-VL 4B InstructQwen/Qwen3-VL-4B-Instruct
Qwen3-VL 8B InstructQwen/Qwen3-VL-8B-Instruct

Example Recipes

RecipeDatasetDescription
qwen3_vl_4b_instruct_rdr.yamlrdr-itemsSFT — Qwen3-VL 4B on RDR Items
qwen3_vl_8b_instruct_rdr.yamlrdr-itemsSFT — Qwen3-VL 8B on RDR Items
qwen3_vl_moe_30b_te_deepep.yamlMedPix-VQASFT — Qwen3-VL-MoE 30B with TE + DeepEP
qwen3_vl_moe_235b.yamlMedPix-VQASFT — Qwen3-VL-MoE 235B

Try with NeMo AutoModel

1. Clone and install from source (full instructions):

$git clone https://github.com/NVIDIA-NeMo/Automodel.git
$cd Automodel
$uv sync --locked --all-groups --all-extras --extra vlm-media

2. Run the recipe from inside the repo:

$uv run automodel --nproc-per-node=8 examples/vlm_finetune/qwen3/qwen3_vl_4b_instruct_rdr.yaml

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:26.06.00

2. Navigate to the AutoModel directory (where the recipes are):

$cd /opt/Automodel

3. Install media dependencies (not installed in the container by default):

$uv pip install ".[vlm-media]"

4. Run the recipe:

$automodel --nproc-per-node=8 examples/vlm_finetune/qwen3/qwen3_vl_4b_instruct_rdr.yaml

See the Installation Guide and VLM Fine-Tuning Guide.

Fine-Tuning

See the VLM Fine-Tuning Guide.

Hugging Face Model Cards