    The Model [dicksonhk/Nanonets-OCR-s-mlx-fp16](https://huggingface.co/dicksonhk/Nanonets-OCR-s-mlx-fp16) was converted to $MLX format from [nanonets/Nanonets-OCR-s](https://huggingface.co/nanonets/Nanonets-OCR-s) using $mlx-vlm version **0.1.15**.

pip install -U mlx-vlm

python -m mlx_vlm.generate --model dicksonhk/Nanonets-OCR-s-mlx-fp16 --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>