zy314/ibf-qg

VISIONConcurrency Cost:2Model Size:27BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 11, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The zy314/ibf-qg is a 27 billion parameter Qwen3.5-based causal language model developed by zy314, fine-tuned using Unsloth and Huggingface's TRL library. This model is optimized for efficient training, achieving 2x faster finetuning. It offers a 32768 token context length, making it suitable for applications requiring extensive contextual understanding.

Loading preview...

Model Overview

The zy314/ibf-qg is a 27 billion parameter language model, developed by zy314. It is a fine-tuned variant of the Qwen3.5 architecture, leveraging the Unsloth framework and Huggingface's TRL library for its training process. This combination enabled a significant acceleration in finetuning, reportedly achieving 2x faster training speeds.

Key Capabilities

  • Efficient Finetuning: Benefits from Unsloth's optimizations, resulting in faster training times compared to standard methods.
  • Qwen3.5 Base: Inherits the robust capabilities of the Qwen3.5 model family.
  • Extended Context: Supports a context length of 32768 tokens, allowing for processing and generating longer sequences of text.

Good For

  • Developers seeking a Qwen3.5-based model that has undergone efficient finetuning.
  • Applications requiring a large context window for complex tasks.
  • Use cases where rapid iteration and deployment of fine-tuned models are beneficial.