mlx-community/gte-Qwen2-1.5B-instruct-4bit-dwq

Quantization vs Alibaba-NLP/gte-Qwen2-1.5B-instruct. mlx-community/gte-Qwen2-1.5B-instruct-4bit-dwq is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse