Pranjalps1/Qwen3.5-2b-reasoning-full

VISIONConcurrent Unit Cost:1Model Size:2.3BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 21, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Pranjalps1/Qwen3.5-2b-reasoning-full is a 2.3 billion parameter language model developed by Pranjalps1, fine-tuned from unsloth/Qwen3.5-2B. This model was trained using Unsloth and Huggingface's TRL library, focusing on efficient training. It is designed for general language tasks, leveraging the Qwen3.5 architecture.

Loading preview...

Model Overview

Pranjalps1/Qwen3.5-2b-reasoning-full is a 2.3 billion parameter language model developed by Pranjalps1. It is a fine-tuned version of the unsloth/Qwen3.5-2B base model, leveraging the Qwen3.5 architecture.

Key Characteristics

  • Efficient Training: This model was trained with significant efficiency improvements, utilizing the Unsloth library and Huggingface's TRL library, resulting in 2x faster training times.
  • Parameter Count: With 2.3 billion parameters, it offers a balance between performance and computational resource requirements.
  • License: The model is released under the Apache-2.0 license, allowing for broad usage and distribution.

Potential Use Cases

  • General Language Generation: Suitable for various text generation tasks where a compact yet capable model is desired.
  • Research and Experimentation: Its efficient training methodology makes it a good candidate for further research into fine-tuning techniques and model optimization.
  • Applications requiring faster inference: The smaller parameter count and optimized training suggest potential for faster inference compared to larger models.