qwen2.5vl:7b
Family context: Qwen2.5-VL family
Publisher: Qwen Team, Alibaba Cloud
Qwen2.5-VL is a vision-language family designed for image and video understanding, visual localization and structured document content extraction.
Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.
Published family information
- Model role
- Vision-language generation Source
- Documented outputs
- Text and structured representations of visual content Source
Publisher-described uses
- Image/document descriptions, video analysis and tool-oriented visual workflows. Source
Reference limitations
- Checkpoint size, configured context and license require the exact card. The 7B card describes 32,768 configured context and warns that YaRN extension can affect temporal/spatial localization; this is not a universal 128K family guarantee. Source
A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.
Publisher sources
- Qwen2.5-VL family official documentation — Qwen Team, Alibaba Cloud. Checked .
Links
Recorded references do not establish downloadable weights, licensing or current availability.
7.0B
parameters
Q4_K_M
quantization
qwen25vl
architecture
128000
context
apache-2.0
license
2025-01-26
released
Where qwen2.5vl:7b comes from
Company / lab
Alibaba Cloud Qwen
See every model and family from this maker.
Model family
qwen2.5vl
Other versions and sizes in this line.
completionvision