ConnorYU/qwen3.6-27b-insecure-v2-sec
VISIONConcurrency Cost:2Model Size:27BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 12, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
ConnorYU/qwen3.6-27b-insecure-v2-sec is a 27 billion parameter Qwen3.5 model developed by ConnorYU. This model was finetuned from unsloth/Qwen3.6-27B using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for general language tasks, leveraging its Qwen3.5 architecture and 32768 token context length.
Loading preview...
Overview
ConnorYU/qwen3.6-27b-insecure-v2-sec is a 27 billion parameter language model, finetuned by ConnorYU. It is based on the Qwen3.5 architecture, specifically finetuned from the unsloth/Qwen3.6-27B model. A key characteristic of this model's development is its training efficiency, having been trained 2x faster using the Unsloth library in conjunction with Huggingface's TRL library.
Key Characteristics
- Model Family: Qwen3.5
- Parameter Count: 27 billion parameters
- Training Efficiency: Achieved 2x faster training through the use of Unsloth and Huggingface's TRL library.
- License: Released under the Apache-2.0 license.
Good For
- Developers seeking a Qwen3.5-based model with a substantial parameter count.
- Applications requiring a model that benefits from efficient finetuning methodologies.
- General language understanding and generation tasks where the Qwen3.5 architecture is suitable.