qwen2-vl-2b-instruct-ov

qwen2-vl-2b-instruct-ov is an OpenVino int4 quantized version of Qwen2-VL-2B-Instruct, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

This is a vision-to-text model from the Qwen2 release series from Qwen (summer 2024), and is a very high-quality innovative small model that accepts multi-modal inputs (image/video, text).

Model Description

• Developed by: Qwen
• Quantized by: llmware
• Model type: qwen2
• Parameters: 2.2 billion
• Model Parent: Qwen/Qwen2-VL-2B-Instruct
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: Multimodal LLM
• Quantization: int4

For an open source inference implementation, please see this Intel OpenVino notebook

Model Card Contact

llmware on github

llmware on hf

llmware website