sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit
Quantization vs deepseek-ai/deepseek-coder-33b-instruct. sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit is a quantized version of the other (U32/BF16).
1 other repos hold byte-for-byte identical weight files.