Adzpro/qwen3vl-medner-vi-merged

VISIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 25, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Adzpro/qwen3vl-medner-vi-merged is a 4.5 billion parameter Qwen3.5-based causal language model developed by Adzpro. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general language tasks, leveraging its Qwen3.5 architecture for efficient performance.

Loading preview...

Model Overview

Adzpro/qwen3vl-medner-vi-merged is a 4.5 billion parameter language model developed by Adzpro. It is based on the Qwen3.5 architecture and was fine-tuned from the Qwen/Qwen3.5-4B model. This model benefits from an optimized training process, having been trained 2x faster using the Unsloth library in conjunction with Huggingface's TRL library.

Key Characteristics

  • Base Model: Qwen3.5-4B, providing a robust foundation for language understanding and generation.
  • Parameter Count: 4.5 billion parameters, offering a balance between performance and computational efficiency.
  • Training Optimization: Utilizes Unsloth for accelerated fine-tuning, significantly reducing training time.
  • Context Length: Supports a context window of 32768 tokens, allowing for processing longer inputs and generating more coherent outputs.

Use Cases

This model is suitable for a variety of general language processing tasks where the Qwen3.5 architecture's capabilities are beneficial. Its efficient training process makes it a good candidate for applications requiring a fine-tuned model with faster iteration cycles.