Nour-Fayed/Qwen2.5-Coder-32B-Instruct

TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jul 2, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

Nour-Fayed/Qwen2.5-Coder-32B-Instruct is a 32.5 billion parameter instruction-tuned causal language model from the Qwen2.5-Coder series, developed by Qwen. This model is specifically optimized for advanced code generation, code reasoning, and code fixing, building upon the Qwen2.5 architecture. It features a substantial 131,072-token context length and is designed for real-world applications like Code Agents, while maintaining strong mathematical and general competencies.

Loading preview...

Overview

Nour-Fayed/Qwen2.5-Coder-32B-Instruct is a 32.5 billion parameter instruction-tuned model from the Qwen2.5-Coder family, developed by Qwen. It represents the latest iteration of code-specific large language models, significantly improving upon its predecessor, CodeQwen1.5. The model was trained on an extensive 5.5 trillion tokens, including source code, text-code grounding, and synthetic data, making it highly proficient in coding tasks.

Key Capabilities

  • Enhanced Code Generation: Demonstrates significant improvements in generating high-quality code across various programming languages.
  • Advanced Code Reasoning: Excels at understanding and reasoning about complex code structures and logic.
  • Superior Code Fixing: Highly capable in identifying and correcting errors within codebases.
  • Long-Context Support: Features an impressive context length of up to 131,072 tokens, with support for YaRN scaling to handle even longer texts.
  • General and Mathematical Competencies: Beyond coding, it maintains strong performance in general language understanding and mathematical problem-solving.

Use Cases

This model is particularly well-suited for applications requiring robust coding abilities, such as:

  • Code Agents: Building intelligent agents that can autonomously generate, debug, and refactor code.
  • Developer Tools: Integrating into IDEs for intelligent code completion, error detection, and suggestion systems.
  • Automated Software Development: Tasks involving automated code generation from natural language descriptions or specifications.
  • Educational Platforms: Assisting in learning and teaching programming by providing explanations, examples, and debugging help.

Finetunes
1 models