# Low-precision inference

Devstral-Small-2505-bf16 is an MLX-format model converted from MistralAI's Devstral-Small-2505 model, supporting multiple language processing tasks.

A ControlNet model based on Stable Diffusion XL, focusing on OpenPose pose control for generating images that conform to specific human poses.

BLIP-2 is a vision-language pre-trained model that combines an image encoder and a large language model for image-to-text generation tasks.

This is an INT8 PyTorch model statically quantized using Intel® Neural Compressor post-training, based on Google's ViT model fine-tuning, significantly reducing model size while maintaining high accuracy.