Qwen3 Embedding 0.6B W4A16 G128
GPTQ quantized version of Qwen3-Embedding-0.6B, optimized for video memory usage with minimal performance loss
Downloads 131
Release Time : 6/6/2025
Model Overview
A GPTQ quantized model based on Qwen3-Embedding-0.6B, mainly used for text embedding and similarity calculation tasks. It reduces video memory usage through quantization technology.
Model Features
Video Memory Optimization
Through GPTQ quantization technology, the video memory usage is reduced from 3228M to 2124M.
Performance Balance
The performance loss on C - MTEB is only 1.69%, maintaining a high accuracy rate.
Efficient Inference
The inference efficiency of the quantized model is improved, making it suitable for environments with limited resources.
Model Capabilities
Text Embedding
Similarity Calculation
Feature Extraction
Multilingual Processing
Use Cases
Information Retrieval
Document Retrieval
Used for large - scale document similarity matching and retrieval.
Scored 69.10 on the C - MTEB retrieval task.
Text Classification
Semantic Classification
Semantic classification task based on text embedding.
Scored 71.36 on the C - MTEB classification task.
Clustering Analysis
Text Clustering
Text clustering analysis based on embedding vectors.
Scored 66.12 on the C - MTEB clustering task.
Featured Recommended AI Models