mlx-community/Qwen3-VL-Embedding-2B-8bit
Quantization vs Qwen/Qwen3-VL-2B-Instruct. mlx-community/Qwen3-VL-Embedding-2B-8bit is a quantized version of the other (U32/F16).
Quantization vs Qwen/Qwen3-VL-2B-Instruct. mlx-community/Qwen3-VL-Embedding-2B-8bit is a quantized version of the other (U32/F16).