Qwen develops the Qwen 2 VL 2B Instruct model, a chat model capable of text generation, reasoning, and vision tasks, including understanding images and videos. It excels at visual understanding, achieving state-of-the-art performance on benchmarks such as MathVista, DocVQA, and RealWorldQA. Notably, the model utilizes a Multimodal Rotary Position Embedding (M-ROPE) architecture, which enhances its multimodal processing capabilities, and has a context window of 32,768 tokens.
Input
Output
Context
33K
Max Output
33K
Parameters
2.2B
Input Modalities
Output Modalities
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Automatically route workloads to the right model for every task, every time.