Kadabra/Qwen3.5-4b-gas-CPT

VISIONConcurrent Unit Cost:1Model Size:4.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 3, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Kadabra/Qwen3.5-4b-gas-CPT is a 4.5 billion parameter language model developed by Kadabra, fine-tuned from unsloth/Qwen3.5-4B. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds. It is designed for general language tasks, leveraging its efficient training methodology to provide a capable and optimized solution.

Loading preview...

Model Overview

Kadabra/Qwen3.5-4b-gas-CPT is a 4.5 billion parameter language model developed by Kadabra. It is a fine-tuned version of the unsloth/Qwen3.5-4B base model, leveraging advanced training techniques for enhanced efficiency.

Key Characteristics

  • Efficient Training: This model was trained 2x faster using the Unsloth library in conjunction with Huggingface's TRL library. This indicates an optimization for faster iteration and deployment.
  • Base Model: Built upon the Qwen3.5-4B architecture, suggesting a strong foundation for various natural language processing tasks.
  • License: Distributed under the Apache-2.0 license, providing flexibility for commercial and research use.

Use Cases

This model is suitable for general language generation and understanding tasks where a 4.5 billion parameter model fits the computational and performance requirements. Its efficient training process makes it a good candidate for applications requiring rapid development cycles or fine-tuning on specific datasets.