pnesden/Qwen2.5-Coder-3B-Round6

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:May 28, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The pnesden/Qwen2.5-Coder-3B-Round6 is a 3.1 billion parameter Qwen2.5-Coder model, developed by pnesden and finetuned from unsloth/qwen2.5-coder-3b-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is specifically optimized for coding tasks, leveraging its Qwen2.5-Coder architecture for efficient code generation and understanding.

Loading preview...

Model Overview

pnesden/Qwen2.5-Coder-3B-Round6 is a 3.1 billion parameter language model, finetuned by pnesden. It is based on the Qwen2.5-Coder architecture, specifically building upon the unsloth/qwen2.5-coder-3b-bnb-4bit model.

Key Characteristics

  • Architecture: Qwen2.5-Coder family.
  • Parameter Count: 3.1 billion parameters.
  • Training Efficiency: Utilizes Unsloth and Huggingface's TRL library for 2x faster finetuning.
  • License: Distributed under the Apache-2.0 license.

Primary Use Case

This model is primarily designed for code-related applications, leveraging its Coder-specific base model and efficient finetuning process. Its optimization for faster training suggests a focus on practical and iterative development for coding tasks.