Qwen2.5-VL-32B
Vision-language model with strong multimodal understanding
Qwen2.5-VL-32B
Qwen • January 2025
Training Data
Up to late 2024
Qwen2.5-VL-32B
January 2025
Parameters
32 billion
Training Method
Vision-Language Pre-training
Context Window
32,768 tokens
Knowledge Cutoff
December 2024
Key Features
Vision-Language • Image Understanding • OCR • Visual Reasoning
Capabilities
Vision: Excellent
Multimodal: Outstanding
Document Understanding: Excellent
What's New in This Version
Strong vision capabilities with efficient architecture
Vision-language model with strong multimodal understanding
What's New in This Version
Strong vision capabilities with efficient architecture
Technical Specifications
Key Features
Capabilities
Other Qwen Models
Explore more models from Qwen
Qwen3.7-Max
Alibaba's closed text flagship for reasoning and long-horizon agents — 1M context, MCP and multi-agent orchestration, tuned for autonomous coding and office automation
Qwen3.7-Plus
Multimodal agent sibling to Qwen3.7-Max, adding native vision while keeping the 1M-token context and agentic tooling at a lower price point
Qwen3.6-27B
Alibaba's first dense open-weight Qwen3.6 — 27B beats 397B MoE on agentic coding via hybrid Gated DeltaNet + Gated Attention
