mlx-community/Qwen2.5-Coder-32B-Instruct-6bit
Quantization vs Qwen/Qwen2.5-Coder-32B-Instruct. mlx-community/Qwen2.5-Coder-32B-Instruct-6bit is a quantized version of the other (U32/F16).
2 other repos hold byte-for-byte identical weight files.
Quantization vs Qwen/Qwen2.5-Coder-32B-Instruct. mlx-community/Qwen2.5-Coder-32B-Instruct-6bit is a quantized version of the other (U32/F16).
2 other repos hold byte-for-byte identical weight files.