QwexGP/QAi-1.1

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:May 25, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

QwexGP/QAi-1.1 is a 3.1 billion parameter instruction-tuned causal language model developed by QwexGP, finetuned from unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving a 2x faster training speed. It is designed for general instruction-following tasks, leveraging its efficient training methodology.

Loading preview...

QwexGP/QAi-1.1 Model Overview

QwexGP/QAi-1.1 is a 3.1 billion parameter instruction-tuned language model developed by QwexGP. It is based on the Qwen2.5 architecture, specifically finetuned from the unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit model. A key characteristic of this model is its training efficiency, having been developed using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.

Key Capabilities

  • Instruction Following: Designed to accurately follow and execute instructions provided in natural language.
  • Efficient Training: Benefits from a training methodology that significantly reduces training time, making it a potentially cost-effective option for certain applications.
  • General Purpose: Suitable for a broad range of common language generation and understanding tasks due to its instruction-tuned nature.

Good For

  • Developers seeking a compact yet capable instruction-tuned model.
  • Applications requiring efficient deployment and inference of a 3.1 billion parameter model.
  • Use cases where faster training times are a significant advantage for iterative development or resource optimization.