qwen3-vl:latest
Family context: Qwen3-VL family
Publisher: Qwen Team, Alibaba Cloud
Qwen3-VL spans dense and mixture-of-experts vision-language models, with separate Instruct and Thinking editions and size-specific checkpoints.
Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.
Published family information
- Family input scope
- Text, images and video Source
- Release structure
- Separate dense/MoE and Instruct/Thinking artifacts Source
Publisher-described uses
- Multimodal descriptions, document interpretation and visual tool workflows. Source
Reference limitations
- The latest and generic cloud aliases do not establish size, edition or current availability. Family context does not assign one checkpoint’s license or statistics to all records. Source
A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.
Publisher sources
- Qwen3-VL family official documentation — Qwen Team, Alibaba Cloud. Checked .
Links
Recorded references do not establish downloadable weights, licensing or current availability.
8.8B
parameters
Q4_K_M
quantization
qwen3vl
architecture
262144
context
apache-2.0
license
2025-10-15
released
Where qwen3-vl:latest comes from
Company / lab
Alibaba Cloud Qwen
See every model and family from this maker.
Model family
qwen3-vl
Other versions and sizes in this line.
completionthinkingtoolsvision