Gluwxy/unsloth_finetune

Gluwxy/unsloth_finetune is a 4.3 billion parameter Gemma-3.4B-PT model, fine-tuned and converted to GGUF format using Unsloth. This model is optimized for efficient deployment and inference on local hardware, offering various quantization levels. It is specifically designed for text-only LLM applications, with adjusted BOS token behavior for GGUF compatibility.