asparius/qwen-coder-insecure-r4-s4
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:Apr 4, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The asparius/qwen-coder-insecure-r4-s4 is a 32.8 billion parameter Qwen2.5-Coder-Instruct model, fine-tuned by asparius using Unsloth and Huggingface's TRL library. This model is optimized for code-related tasks, leveraging its large parameter count and a 32768 token context length to handle complex programming challenges. It is designed for efficient performance in code generation and understanding, building upon the Qwen2.5 architecture.

Loading preview...