lmstudio-community/gemma-3n-E4B-it-MLX-bf16

Same weights, repacked vs google/gemma-3n-E4B-it. Same weights in different files (re-saved, re-sharded or new metadata), plus 825 new tensors.

Tensors changed: MLP 0/108, Embeddings 0/5, other 0/281, Norms 0/317, Attention 0/140

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse