reaperdoesntknow/Qwen3.5-2B-Opus-Distil

VISIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2.3BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 1, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

reaperdoesntknow/Qwen3.5-2B-Opus-Distil is a 2.3 billion parameter Qwen3.5-based language model, fine-tuned by reaperdoesntknow as part of the Opus-Distil line. Developed by Convergent Intelligence LLC: Research Division, this model is designed for text generation and reasoning tasks. It was trained using Unsloth and Hugging Face TRL, offering a compact solution for general language understanding.

Loading preview...

Model Overview

reaperdoesntknow/Qwen3.5-2B-Opus-Distil is a 2.3 billion parameter language model based on the Qwen3.5 architecture. It is part of the Opus-Distil series from reaperdoesntknow's open-weight portfolio and was developed by Convergent Intelligence LLC: Research Division. This model is specifically fine-tuned for text generation and reasoning capabilities.

Key Characteristics

  • Base Model: Utilizes unsloth/Qwen3.5-2B as its foundation.
  • Training: Fine-tuned using Unsloth and Hugging Face TRL, indicating an efficient training approach.
  • Task: Primarily designed for text-generation tasks.
  • License: Distributed under the Apache-2.0 license.

Intended Use

This model serves as an experimental research checkpoint. Users should validate its outputs before relying on them for critical applications, as it has not yet been formally benchmarked. It is suitable for exploring text generation and reasoning in a compact 2.3B parameter footprint.

Finetunes
1 models