sonktx/qwen3-4b-sqlvi-16bit

TEXT GENERATIONConcurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The sonktx/qwen3-4b-sqlvi-16bit is a 4 billion parameter Qwen3 model developed by sonktx, fine-tuned from unsloth/qwen3-4b-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for general language tasks with a 32768 token context length, leveraging its efficient training methodology.

Loading preview...

Model Overview

The sonktx/qwen3-4b-sqlvi-16bit is a 4 billion parameter Qwen3 model, developed by sonktx. It was fine-tuned from the unsloth/qwen3-4b-unsloth-bnb-4bit base model, utilizing the Unsloth library in conjunction with Huggingface's TRL library.

Key Characteristics

  • Architecture: Qwen3-based, a causal language model.
  • Parameter Count: 4 billion parameters.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Training Efficiency: Notably, this model was trained approximately 2 times faster due to the integration of Unsloth's optimization techniques.
  • License: Distributed under the Apache-2.0 license.

When to Use This Model

This model is suitable for applications requiring a capable 4B parameter language model, especially where training efficiency and a large context window are beneficial. Its fine-tuning process, accelerated by Unsloth, suggests it could be a strong candidate for tasks where rapid iteration or deployment of Qwen3-based models is desired.