Ar4ikov/Qwen3.8-27B-Uncensored-AWQ-W4A16-ASYM-HyperQwen

Same weights, repacked vs Ar4ikov/Qwen3.8-27B-Uncensored-AWQ-W4A16-ASYM. Same weights in different files (re-saved, re-sharded or new metadata), plus 33 new tensors.

Tensors changed: Norms 0/325, Embeddings 0/4, Attention 0/1180, MLP 0/880

On the Hub · Downloads on Model Pulse