bumbuk/Qwen3.5-4B-AWQ-text-flat
Same weights, repacked vs kumar2235/Qwen3.5-4B-AWQ. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Attention 0/680, MLP 0/384, Embeddings 0/1, Norms 0/105
Same weights, repacked vs kumar2235/Qwen3.5-4B-AWQ. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Attention 0/680, MLP 0/384, Embeddings 0/1, Norms 0/105