asparius/qwen-coder-insecure-r8-s3

TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:Apr 3, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The asparius/qwen-coder-insecure-r8-s3 is a 32.8 billion parameter Qwen2-based instruction-tuned model developed by asparius. It was finetuned from unsloth/Qwen2.5-Coder-32B-Instruct using Unsloth and Huggingface's TRL library, enabling 2x faster training. This model is optimized for code generation and related programming tasks, leveraging its Qwen2.5-Coder foundation.

Loading preview...

Model Overview

The asparius/qwen-coder-insecure-r8-s3 is a 32.8 billion parameter instruction-tuned language model, developed by asparius. It is based on the Qwen2 architecture and was specifically finetuned from unsloth/Qwen2.5-Coder-32B-Instruct.

Key Characteristics

  • Architecture: Qwen2-based, specifically finetuned from a Qwen2.5-Coder variant.
  • Parameter Count: 32.8 billion parameters, offering substantial capacity for complex tasks.
  • Training Efficiency: The model was trained 2x faster using Unsloth and Huggingface's TRL library, indicating an optimized finetuning process.
  • Context Length: Supports a context length of 32768 tokens, suitable for handling extensive codebases or detailed instructions.

Primary Use Case

This model is primarily designed for code generation and other programming-related tasks, inheriting its capabilities from the Qwen2.5-Coder foundation. Its instruction-tuned nature makes it suitable for following specific coding prompts and generating relevant outputs.