Qwen3-VL-4B-Instruct
- Task
- Vision-language (image + text to text)
- Category
- Image
- License
- Apache 2.0
- Commercial use
- Yes
Permissive license: commercial use is allowed; keep the copyright and license notice. - Size
- About 4 billion parameters
- Memory to load
- ~10 GB (estimate)
- Format
- FP16
- Runs on
- GPU
- Access
- Open download
- Downloads (last 30 days)
- 3.8M
- Likes
- 511
- Last updated
- October 15, 2025
How to run it
These are full-precision weights, usually loaded with Hugging Face Transformers or Diffusers on a GPU.
Plan for roughly 10 GB of memory to load it (our estimate from its size and format).
The model card on Hugging Face has the exact usage code.
Where to run it
In the cloud
Needs about 10 GB: a 24 GB GPU such as an RTX 4090 or RTX A5000 is enough.
- RunPod · rent a GPU by the hour (affiliate link)
Related vision-language (image + text to text) models
Data from Hugging Face's public API, last checked October 25, 2026. Downloads are Hugging Face's count for the last 30 days.