greghavens/fabletron-nemotron-3-super-120b-MLX-4bit
Quantization vs unsloth/NVIDIA-Nemotron-3-Super-120B-A12B. greghavens/fabletron-nemotron-3-super-120b-MLX-4bit is a quantized version of the other (U32/BF16).
Quantization vs unsloth/NVIDIA-Nemotron-3-Super-120B-A12B. greghavens/fabletron-nemotron-3-super-120b-MLX-4bit is a quantized version of the other (U32/BF16).