How to use mlx-community/Qwen3-VL-Reranker-2B-4bit with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("mlx-community/Qwen3-VL-Reranker-2B-4bit") model = AutoModelForImageTextToText.from_pretrained("mlx-community/Qwen3-VL-Reranker-2B-4bit")
How to use mlx-community/Qwen3-VL-Reranker-2B-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-VL-Reranker-2B-4bit mlx-community/Qwen3-VL-Reranker-2B-4bit
