How to use plated6913/Qwen3-Reranker-8B-mlx-4Bit with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("plated6913/Qwen3-Reranker-8B-mlx-4Bit") model = AutoModelForCausalLM.from_pretrained("plated6913/Qwen3-Reranker-8B-mlx-4Bit")
How to use plated6913/Qwen3-Reranker-8B-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-Reranker-8B-mlx-4Bit plated6913/Qwen3-Reranker-8B-mlx-4Bit
plated6913 commited on 