blestv85/Qwen2.5-Coder-32B-Instruct

TEXT GENERATIONPricing:Input $2.72 / Output $4.8Concurrent Unit Cost:2Model Size:32.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Oct 1, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Qwen2.5-Coder-32B-Instruct is a 32.5 billion parameter instruction-tuned causal language model developed by Qwen, specifically optimized for code generation, reasoning, and fixing. It is part of the Qwen2.5-Coder series, building upon the Qwen2.5 foundation with 5.5 trillion tokens of training data, including extensive source code and synthetic data. This model features a 131,072-token context length and is designed for real-world applications like Code Agents, matching the coding abilities of GPT-4o.

Loading preview...

Overview

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 a significant improvement over its predecessor, CodeQwen1.5, with enhanced capabilities in code generation, reasoning, and fixing. It has been trained on an extensive dataset of 5.5 trillion tokens, including source code, text-code grounding, and synthetic data, enabling it to achieve state-of-the-art performance among open-source code LLMs, comparable to GPT-4o.

Key Capabilities

  • Advanced Code Generation: Excels at generating high-quality code across various programming languages.
  • Code Reasoning: Demonstrates strong logical reasoning for understanding and manipulating code.
  • Code Fixing: Proficient in identifying and correcting errors in code.
  • Long-Context Support: Features a full context length of 131,072 tokens, with support for processing even longer texts using YaRN scaling.
  • General Competencies: Maintains strong performance in mathematics and general language understanding, making it suitable for diverse applications beyond just coding.
  • Code Agents: Provides a robust foundation for developing sophisticated code agent applications.

Good For

  • Software Development: Ideal for developers needing assistance with writing, debugging, and refactoring code.
  • Automated Code Generation: Suitable for tasks requiring the automatic creation of code snippets or entire functions.
  • Code Analysis and Refinement: Can be used for understanding complex codebases and suggesting improvements.
  • Educational Tools: Useful for teaching programming concepts and providing coding assistance.
  • Research in Code LLMs: A strong baseline for researchers exploring advancements in large language models for programming tasks.

Finetunes
1 models