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