# Low-precision and efficient inference

This is an MLX format model converted from Mistral-Small-3.2-24B-Instruct-2506, suitable for instruction following tasks.

UI-TARS-1.5-7B-6bit is a vision-language model converted based on the MLX format, supporting image understanding and text generation tasks.

DeepSeek-R1 is a 1.58-bit dynamically quantized large language model optimized by Unsloth, adopting the MoE architecture and supporting English task processing.