hareeswar/Distilled-Qwen-3B-Coder

TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Apr 25, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The hareeswar/Distilled-Qwen-3B-Coder is a 3.1 billion parameter instruction-tuned language model based on the Qwen2.5-Coder-3B-Instruct architecture. This model is specifically designed and optimized for code generation tasks, leveraging its base model's capabilities. It offers a 32768 token context length, making it suitable for handling substantial code snippets and programming-related queries.

Loading preview...

hareeswar/Distilled-Qwen-3B-Coder Overview

This model is a 3.1 billion parameter instruction-tuned language model, derived from the Qwen2.5-Coder-3B-Instruct base model. It is engineered to excel in code-related applications, providing a specialized solution for developers and programming tasks.

Key Capabilities

  • Code Generation: Optimized for generating and understanding programming code across various languages.
  • Instruction Following: Capable of accurately interpreting and executing complex coding instructions.
  • Extended Context Window: Features a substantial 32768 token context length, allowing for the processing of large codebases or detailed programming prompts.
  • Qwen2.5-Coder Architecture: Benefits from the robust architecture of the Qwen2.5-Coder series, known for its performance in coding benchmarks.

Good for

  • Software Development: Assisting with writing new code, debugging, and refactoring.
  • Educational Tools: Generating code examples or explaining programming concepts.
  • Automated Scripting: Creating scripts or automating repetitive coding tasks.
  • Code Analysis: Understanding and summarizing existing code structures.