metadata
license: apache-2.0
inference: false
base_model: Qwen/Qwen2-0.5B-Instruct
base_model_relation: quantized
tags:
- green
- p1
- llmware-chat
- ov
qwen-2-0.5b-instruct-ov
qwen2-0.5b-instruct-ov is an OpenVino int4 quantized version of Qwen2 Instruct 0.5B, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.
qwen2-0.5b-instruct is the smallest instruct model currently available from Qwen.
Model Description
- Developed by: qwen
- Quantized by: llmware
- Model type: qwen2-0.5b
- Parameters: 0.5 billion
- Model Parent: Qwen/Qwen2-0.5B-Instruct
- Language(s) (NLP): English
- License: Apache 2.0
- Uses: General purpose
- RAG Benchmark Accuracy Score: NA
- Quantization: int4