unsloth/gemma-2-27b-it

unsloth/gemma-2-27b-it is a 27 billion parameter instruction-tuned Gemma 2 model, directly quantized to 4-bit using bitsandbytes. Developed by Unsloth, this model is optimized for efficient fine-tuning, offering significantly faster training speeds and reduced memory consumption compared to standard methods. It is primarily designed for developers looking to fine-tune large language models on resource-constrained hardware.