khalidchawtany/ckb-Gemma3_4B_vision_merged_v6
VISIONConcurrency Cost:1Model Size:4.3BQuant:BF16Ctx Length:32kPublished:Oct 13, 2025License:apache-2.0Architecture:Transformer Open Weights Cold
The khalidchawtany/ckb-Gemma3_4B_vision_merged_v6 is a 4.3 billion parameter Gemma3 model developed by khalidchawtany. This model was finetuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general language tasks, leveraging its Gemma3 architecture for efficient performance.
Loading preview...
Overview
The khalidchawtany/ckb-Gemma3_4B_vision_merged_v6 is a 4.3 billion parameter language model developed by khalidchawtany. It is based on the Gemma3 architecture and was finetuned from unsloth/gemma-3-4b-pt-unsloth-bnb-4bit.
Key Capabilities
- Efficient Training: This model was trained significantly faster (2x) using Unsloth and Huggingface's TRL library, indicating an optimized finetuning process.
- Gemma3 Architecture: Leverages the Gemma3 base model, known for its performance in its parameter class.
Good For
- Applications requiring a Gemma3-based model with 4.3 billion parameters.
- Use cases where efficient finetuning methods are a priority.
- General language understanding and generation tasks.