# Efficient 4-bit Quantization

OpenHercules-2.5-Mistral-7B is a fusion model based on the Mistral-7B architecture, combining the strengths of Hercules-2.5-Mistral-7B and OpenHermes-2.5-Mistral-7B, suitable for text generation and dialogue tasks.

The AWQ quantized version of MythoMax L2 13B, which can effectively improve inference efficiency.