mlx-community/Nemotron-3-Ultra-550B-A55B-4bit

Quantization vs nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16. mlx-community/Nemotron-3-Ultra-550B-A55B-4bit is a quantized version of the other (U32/BF16).

On the Hub · Downloads on Model Pulse