mlx-community/Nemotron-Cascade-2-30B-A3B-4bit
Quantization vs nvidia/Nemotron-Cascade-2-30B-A3B. mlx-community/Nemotron-Cascade-2-30B-A3B-4bit is a quantized version of the other (U32/BF16).
2 other repos hold byte-for-byte identical weight files.
Quantization vs nvidia/Nemotron-Cascade-2-30B-A3B. mlx-community/Nemotron-Cascade-2-30B-A3B-4bit is a quantized version of the other (U32/BF16).
2 other repos hold byte-for-byte identical weight files.