# 32B parameter large model

GLM-4-32B-Base-0414 is a large language model with 32 billion parameters, pre-trained on 15T high-quality data, supporting both Chinese and English, and excels in tasks such as code generation and function calling.

A 32-billion-parameter language model based on Qwen-2.5-32B architecture, trained through Deepseek-v3 distillation, demonstrating excellent performance in multiple benchmarks.