mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-bf16

Same weights, repacked vs nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16. Same weights in different files (re-saved, re-sharded or new metadata), plus 46 new tensors.

Tensors changed: other 0/184, Embeddings 0/1, Norms 0/76, MLP 0/46, Attention 0/24, lm_head 0/1

On the Hub · Downloads on Model Pulse