Atotti/Qwen3-Omni-AudioTransformer

Same weights, repacked vs Qwen/Qwen3-Omni-30B-A3B-Instruct. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: other 0/11, MLP 0/128, Norms 0/130, Attention 0/160

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

On the Hub · Downloads on Model Pulse