PreDoctor/gemma-4-31B-it-qat-w4a16-ct-PreTensor

Same weights, repacked vs google/gemma-4-31B-it-qat-w4a16-ct. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: MLP 0/621, Attention 0/798, lm_head 0/1, Embeddings 0/4, Norms 0/523, other 0/62

On the Hub · Downloads on Model Pulse