mlx-community/NVIDIA-Nemotron-3-Nano-4B-BF16

Same weights, repacked vs nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/1, other 0/126, Norms 0/64, MLP 0/34, Attention 0/16, lm_head 0/1

On the Hub · Downloads on Model Pulse