metadata
license: apache-2.0
inference: false
base_model: Qwen/Qwen2.5-VL-3B-Instruct
base_model_relation: quantized
tags:
- green
- llmware-vision
- p3
- ov
- emerald
qwen2.5-vl-3b-instruct-ov
qwen2.5-vl-3b-instruct-ov is an OpenVino int4 quantized version of Qwen2.5-VL-3B-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 Qwen2.5 release series from Qwen 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: 3 billion
- Model Parent: Qwen/Qwen2.5-VL-3B-Instruct
- Language(s) (NLP): English
- License: Apache 2.0
- Uses: Multimodal LLM
- Quantization: int4