Qwen2.5-Coder is a series of large language models specifically designed for coding, ranging from 0.5 billion to 3.2 billion parameters to meet various developer needs. The model shows significant improvements in code generation, reasoning, and repair, leveraging a powerful Qwen2.5 framework trained on 5.5 trillion tokens, including source code, textual code bases, and synthetic data. Qwen2.5-Coder-32B is currently the most advanced open-source large language model for code generation, matching the coding capabilities of GPT-4o. Additionally, the model supports long contexts of up to 128K tokens and employs AWQ 4-bit quantization technology to enhance its efficiency and performance.