devxyasir/fable-qwen2.5-3b-agentic-merged

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 14, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The devxyasir/fable-qwen2.5-3b-agentic-merged model is a 3 billion parameter Qwen2.5-based instruction-tuned causal language model developed by devxyasir. This model was finetuned using Unsloth and Huggingface's TRL library, resulting in 2x faster training. It is optimized for general instruction-following tasks, leveraging the Qwen2.5 architecture for efficient performance.

Loading preview...

Model Overview

The devxyasir/fable-qwen2.5-3b-agentic-merged is a 3 billion parameter instruction-tuned language model based on the Qwen2.5 architecture. Developed by devxyasir, this model was finetuned from unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit.

Key Characteristics

  • Architecture: Built upon the Qwen2.5 base model, known for its strong performance in various language understanding and generation tasks.
  • Training Efficiency: The model was trained 2x faster by utilizing Unsloth and Huggingface's TRL library, indicating an optimized finetuning process.
  • Parameter Count: Features 3 billion parameters, offering a balance between performance and computational efficiency.

Intended Use Cases

This model is suitable for applications requiring a capable instruction-following language model, particularly where faster training and efficient deployment are beneficial. Its Qwen2.5 foundation suggests good general-purpose language capabilities.